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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 3894
    Prev
    Next
    INDEX
    Explanations

    references to neo or neo-related terms, particularly in political or social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ĭ
    -0.15
     Rosenberg
    -0.15
    idable
    -0.15
    gree
    -0.14
    оваÑĢ
    -0.13
     Transitional
    -0.13
    rella
    -0.13
    глÑıд
    -0.13
    ADATA
    -0.13
     inan
    -0.13
    POSITIVE LOGITS
    cons
    0.26
    -Nazi
    0.22
    -cons
    0.22
     cons
    0.20
    CONS
    0.19
    -lib
    0.19
    Äįek
    0.19
     classical
    0.18
    -class
    0.17
    ÅĻich
    0.17
    Activations Density 0.007%

    No Known Activations