© 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. 17-LLAMASCOPE-RES-131K
    11. 104683
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence or verification of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ave
    -0.07
    é¨
    -0.07
     Bart
    -0.06
    bsolute
    -0.06
    _KIND
    -0.06
    ovny
    -0.06
    jÃł
    -0.06
    άÏĤ
    -0.06
    aves
    -0.06
    arpa
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.07
    stown
    0.07
    ora
    0.06
    chandle
    0.06
    871
    0.06
    ileo
    0.06
    hiba
    0.06
     Limits
    0.06
     cheek
    0.06
    .Override
    0.06
    Activations Density 0.000%

    No Known Activations