© 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. 18-LLAMASCOPE-RES-32K
    11. 5701
    Prev
    Next
    INDEX
    Explanations

    the presence of specific suffix patterns in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AMAGE
    -0.18
    ýt
    -0.15
    itude
    -0.15
    /xhtml
    -0.15
    rn
    -0.15
    áno
    -0.14
    .toObject
    -0.14
    çº
    -0.14
    olini
    -0.14
    र
    -0.14
    POSITIVE LOGITS
    adt
    0.20
    ead
    0.18
    ein
    0.17
    ensa
    0.17
    hetics
    0.16
    tte
    0.16
    jerne
    0.16
    asis
    0.16
    اسب
    0.15
    igm
    0.15
    Activations Density 0.056%

    No Known Activations