© 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. 17-LLAMASCOPE-RES-131K
    6. 74595
    Prev
    Next
    INDEX
    Explanations

    references to various identities and ethnicities

    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
    itra
    -0.07
    irement
    -0.07
    одеÑĢж
    -0.07
    oko
    -0.07
    abase
    -0.07
    Ñĸг
    -0.07
    igham
    -0.06
    orgia
    -0.06
    лÑĸв
    -0.06
    orro
    -0.06
    POSITIVE LOGITS
     reconc
    0.08
    isch
    0.07
    bred
    0.07
    /******/
    0.07
     enough
    0.06
    /WebAPI
    0.06
    å¼¥
    0.06
    uell
    0.06
    /Set
    0.05
    ãĥ¼ãĥľ
    0.05
    Activations Density 0.021%

    No Known Activations