© 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. 126392
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to innovation

    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
    istrovstvÃŃ
    -0.07
    quo
    -0.07
    loid
    -0.07
    phalt
    -0.07
    acher
    -0.07
    loor
    -0.07
    jang
    -0.07
    uru
    -0.07
    yo
    -0.07
    unto
    -0.07
    POSITIVE LOGITS
    herent
    0.07
    /new
    0.07
    lette
    0.07
    LETTE
    0.07
    elly
    0.06
    /original
    0.06
    removeAttr
    0.06
    .bio
    0.06
    -Mar
    0.06
    liž
    0.06
    Activations Density 0.011%

    No Known Activations