© 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. 890
    Prev
    Next
    INDEX
    Explanations

    alternative suggestions or options

    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
    anco
    -0.07
    TD
    -0.06
    /wiki
    -0.06
    ago
    -0.06
    кÑĸн
    -0.06
    /DD
    -0.06
     itself
    -0.06
    addle
    -0.06
    ensual
    -0.06
    atus
    -0.05
    POSITIVE LOGITS
    ignal
    0.08
    vig
    0.07
    riad
    0.07
    anges
    0.07
    HEET
    0.07
    ieux
    0.06
    ambi
    0.06
    subcategory
    0.06
    378
    0.06
    pag
    0.06
    Activations Density 0.004%

    No Known Activations