© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 2-LLAMASCOPE-RES-32K
    11. 7413
    Prev
    Next
    INDEX
    Explanations

    the concept of a safe or protective space, often symbolized by the word "sanctuary."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģķãģ¾
    -0.16
    .UnitTesting
    -0.15
    rief
    -0.15
    cean
    -0.14
    uvre
    -0.14
    ctors
    -0.14
    ÅĻe
    -0.14
    patch
    -0.14
    ULA
    -0.14
    adh
    -0.14
    POSITIVE LOGITS
     Rew
    0.18
    adoo
    0.17
    492
    0.16
    ettings
    0.15
     rew
    0.14
    дÑĢеÑģ
    0.14
    zcze
    0.14
    utow
    0.13
     manifest
    0.13
     Gret
    0.13
    Activations Density 0.007%

    No Known Activations