© 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. 61262
    Prev
    Next
    INDEX
    Explanations

    emotionally charged moments in personal interactions

    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
    rokes
    -0.07
    .DropDown
    -0.07
    ereotype
    -0.06
    kers
    -0.06
    tual
    -0.06
    rowsable
    -0.06
     blinking
    -0.06
    .rs
    -0.06
    .TableName
    -0.06
    eriod
    -0.06
    POSITIVE LOGITS
     tonight
    0.07
    jos
    0.06
    asan
    0.06
     terminal
    0.06
    ilde
    0.06
     familiar
    0.06
     usual
    0.06
    vette
    0.06
    oleÄį
    0.05
    loquent
    0.05
    Activations Density 0.255%

    No Known Activations