© 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. 40305
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting symbols

    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
    ej
    -0.06
    ppers
    -0.06
     Webster
    -0.06
     Tier
    -0.06
    ingu
    -0.06
     overhe
    -0.05
    tte
    -0.05
    ckt
    -0.05
    ade
    -0.05
    iddi
    -0.05
    POSITIVE LOGITS
    Q
    0.10
     Q
    0.10
    ilon
    0.07
    itsu
    0.07
    qed
    0.07
     QUESTION
    0.07
    ,Q
    0.07
    QDebug
    0.07
     question
    0.07
     interviewer
    0.07
    Activations Density 0.096%

    No Known Activations