© 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. 103680
    Prev
    Next
    INDEX
    Explanations

    terms related to community service and social responsibility

    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
    å¾ħ
    -0.07
    reten
    -0.07
    ÅĻÃŃt
    -0.07
    agan
    -0.07
    ãĤ¤ãĤ¯
    -0.06
    ango
    -0.06
    anta
    -0.06
    aÄį
    -0.06
    acher
    -0.06
    onen
    -0.06
    POSITIVE LOGITS
    ERRU
    0.07
    ItemAt
    0.07
    latlong
    0.07
     Lad
    0.07
    ccione
    0.07
    lags
    0.06
    ationToken
    0.06
    ضÙĪ
    0.06
    upe
    0.06
    ropy
    0.06
    Activations Density 0.038%

    No Known Activations