© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 12-LLAMASCOPE-RES-32K
    11. 17997
    Prev
    Next
    INDEX
    Explanations

    phrases related to beginnings, promises, and the essence of a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stable
    -0.16
    stag
    -0.15
    itan
    -0.15
     Pant
    -0.14
    ativa
    -0.13
    eling
    -0.13
     íijľ
    -0.13
    ivot
    -0.13
    ativas
    -0.13
     Ere
    -0.13
    POSITIVE LOGITS
    .tw
    0.15
    isel
    0.15
    ãĥĥãĤ·ãĥ¥
    0.15
    æ¦Ĥ
    0.15
    umm
    0.14
    inaire
    0.14
    .truth
    0.14
    ÏĥÏĢ
    0.14
    νÏĦ
    0.14
    anol
    0.14
    Activations Density 0.121%

    No Known Activations