© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14847
    Prev
    Next
    INDEX
    Explanations

    references to specific characters or terms related to cultural or contextual analysis

    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
    ateria
    -0.06
    ataire
    -0.06
    ACHINE
    -0.06
    isque
    -0.06
    ffffffff
    -0.06
    Sentence
    -0.06
    229
    -0.06
    alcon
    -0.06
    iona
    -0.06
    äh
    -0.05
    POSITIVE LOGITS
    Victoria
    0.07
    opak
    0.06
     Schwar
    0.06
    ileaks
    0.06
    ÄĽÅĻ
    0.06
    ë³µ
    0.06
     VÆ°Æ¡ng
    0.06
     deleg
    0.06
     sécur
    0.06
     Mã
    0.06
    Activations Density 0.010%

    No Known Activations