© 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. 82573
    Prev
    Next
    INDEX
    Explanations

    statements related to explanations or analytical viewpoints

    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
    éĢ
    -0.07
    ém
    -0.07
    inic
    -0.07
    ãĢĤãĢĤ↵↵
    -0.06
    }elseif
    -0.06
    .Results
    -0.06
     ðŁĺī↵↵
    -0.06
    inds
    -0.06
    -after
    -0.06
    icz
    -0.06
    POSITIVE LOGITS
    hardt
    0.07
     yes
    0.07
    foy
    0.07
    ä½ł
    0.06
     answered
    0.06
     your
    0.06
     you
    0.06
    μη
    0.06
     FW
    0.06
    foil
    0.06
    Activations Density 0.052%

    No Known Activations