© 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. 20-LLAMASCOPE-RES-32K
    11. 29423
    Prev
    Next
    INDEX
    Explanations

    references to hierarchical structures and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -opacity
    -0.16
    /ay
    -0.16
    gere
    -0.14
    verity
    -0.14
    vd
    -0.13
    /ip
    -0.13
    VERN
    -0.13
    lobal
    -0.13
    olicit
    -0.13
    ụn
    -0.13
    POSITIVE LOGITS
    /target
    0.26
    /source
    0.26
    -side
    0.24
    /reference
    0.22
     Side
    0.18
    /master
    0.18
     SIDE
    0.17
    side
    0.16
     side
    0.16
     party
    0.16
    Activations Density 0.347%

    No Known Activations