© 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. 15-LLAMASCOPE-RES-131K
    6. 104029
    Prev
    Next
    INDEX
    Explanations

    terms related to authenticity and representation in storytelling

    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
    .PropTypes
    -0.07
    /**<
    -0.07
    (çģ«
    -0.06
     Hayward
    -0.06
    (æľ¨
    -0.06
     Gay
    -0.06
     bast
    -0.06
    åŁĭ
    -0.06
     ReSharper
    -0.06
     spol
    -0.06
    POSITIVE LOGITS
    ame
    0.07
    BSD
    0.06
    chod
    0.06
    оÑĢÑĥ
    0.06
    $MESS
    0.06
    anus
    0.06
    orno
    0.06
     âĢIJ
    0.06
    "urls
    0.06
    onders
    0.06
    Activations Density 0.000%

    No Known Activations