© 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. 87716
    Prev
    Next
    INDEX
    Explanations

    references to significant personal experiences and challenges

    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
    illo
    -0.07
    ephir
    -0.07
    ValueCollection
    -0.07
    ICODE
    -0.07
    Cancelable
    -0.07
    dül
    -0.07
    avern
    -0.07
    _escape
    -0.07
    FTA
    -0.07
    丸
    -0.07
    POSITIVE LOGITS
     '
    0.08
     "
    0.07
     was
    0.06
    indir
    0.06
     ''
    0.06
     lasting
    0.06
    'T
    0.06
    821
    0.06
     reaction
    0.06
    FI
    0.05
    Activations Density 0.048%

    No Known Activations