© 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. 74192
    Prev
    Next
    INDEX
    Explanations

    instances of the word "alternate" and its variations

    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
    essian
    -0.08
    /ay
    -0.07
    lid
    -0.07
    ification
    -0.07
    /board
    -0.07
    zcze
    -0.07
    koli
    -0.07
    ç¬
    -0.07
    rame
    -0.06
    ãĥĥãĤ«ãĥ¼
    -0.06
    POSITIVE LOGITS
     between
    0.09
    vely
    0.09
    ingly
    0.09
    Endian
    0.08
    endo
    0.08
     междÑĥ
    0.07
     altern
    0.07
    ally
    0.07
    atively
    0.07
    boro
    0.07
    Activations Density 0.004%

    No Known Activations