Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96204
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods

    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
    landa
    -0.07
    bao
    -0.07
    rait
    -0.07
    bay
    -0.07
    lando
    -0.07
    iese
    -0.07
    uais
    -0.07
    iras
    -0.07
    cancellationToken
    -0.07
    itchens
    -0.07
    POSITIVE LOGITS
    ten
    0.07
     dish
    0.06
    oplast
    0.06
     dub
    0.06
     
    0.05
    'ye
    0.05
    425
    0.05
     "
    0.05
    Ïĥκε
    0.05
     shrink
    0.05
    Activations Density 0.026%

    No Known Activations