© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 16057
    Prev
    Next
    INDEX
    Explanations

    references to family relationships

    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
     fing
    -0.06
    елов
    -0.06
     Misc
    -0.06
     Mood
    -0.06
    aar
    -0.06
    hum
    -0.06
    øj
    -0.05
     elek
    -0.05
    /effects
    -0.05
     misc
    -0.05
    POSITIVE LOGITS
    ansson
    0.08
     Exped
    0.08
    geom
    0.07
    oldur
    0.07
    اÙĬت
    0.07
    anoia
    0.07
    _cou
    0.07
    .TRA
    0.07
    aktiv
    0.06
    ãĥ³ãĥĶ
    0.06
    Activations Density 0.000%

    No Known Activations