© 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. 78306
    Prev
    Next
    INDEX
    Explanations

    references to families and personal 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
    ourg
    -0.08
    iasm
    -0.07
    avirus
    -0.06
     Vict
    -0.06
    _defs
    -0.06
    asad
    -0.06
    ARSER
    -0.06
    Ñĸв
    -0.06
    rate
    -0.06
    avax
    -0.06
    POSITIVE LOGITS
     remar
    0.08
    .scalablytyped
    0.07
    emd
    0.07
    ozÃŃ
    0.07
    CTX
    0.07
    /WebAPI
    0.06
     ALOG
    0.06
    emotion
    0.06
    ernetes
    0.06
    _mC
    0.06
    Activations Density 0.026%

    No Known Activations