© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 21-LLAMASCOPE-RES-32K
    6. 19991
    Prev
    Next
    INDEX
    Explanations

    terms associated with different artistic movements and ideologies, particularly those linked to surrealism, nihilism, and various forms of social commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elon
    -0.16
    WISE
    -0.16
    Globals
    -0.15
     Gre
    -0.15
    imar
    -0.14
     Mei
    -0.14
     Imm
    -0.14
    onde
    -0.14
     gre
    -0.14
    Gre
    -0.14
    POSITIVE LOGITS
    ist
    0.62
    ism
    0.60
    ists
    0.58
    istic
    0.52
    主ä¹ī
    0.46
    ISM
    0.39
    IST
    0.38
    ismus
    0.36
    iste
    0.35
    ista
    0.35
    Activations Density 0.101%

    No Known Activations