© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 87601
    Prev
    Next
    INDEX
    Explanations

    references to specific software programs and their related versions or components

    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
     же
    -0.07
     ones
    -0.07
     of
    -0.06
     Platz
    -0.06
    andle
    -0.06
    ward
    -0.06
     and
    -0.06
    ale
    -0.06
     Hass
    -0.06
     merupakan
    -0.06
    POSITIVE LOGITS
     Paz
    0.07
    aeper
    0.07
    ekim
    0.07
    309
    0.07
    NCY
    0.06
    iento
    0.06
    opup
    0.06
    BeenCalled
    0.06
    /XMLSchema
    0.06
    286
    0.06
    Activations Density 0.035%

    No Known Activations