© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 29-LLAMASCOPE-RES-32K
    6. 3651
    Prev
    Next
    INDEX
    Explanations

    elements related to policy definitions and controls within a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ":"","
    -0.19
     latter
    -0.19
    __;
    -0.18
    ":""
    -0.16
     [];
    -0.16
     ""),
    -0.16
    noinspection
    -0.16
    ();
    -0.16
    --;
    -0.15
     '';
    -0.15
    POSITIVE LOGITS
    ,↵
    0.86
    (),↵
    0.69
    ,↵↵
    0.68
    ",↵
    0.67
     ,↵
    0.66
    ',↵
    0.64
    _,↵
    0.64
    .,↵
    0.61
    ,č↵
    0.61
     [],↵
    0.59
    Activations Density 0.578%

    No Known Activations