© 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. 78285
    Prev
    Next
    INDEX
    Explanations

    exclamation points and expressions of enthusiasm

    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
    ãĤĪãģŃ
    -0.08
     Wikipedia
    -0.07
    ÑĢаÑĩ
    -0.07
    ãĥ³ãĥij
    -0.06
    ique
    -0.06
    IMO
    -0.06
     wikipedia
    -0.06
     Rao
    -0.06
     neo
    -0.06
    155
    -0.06
    POSITIVE LOGITS
    adil
    0.08
    aval
    0.08
    вай
    0.07
    @update
    0.07
    update
    0.07
    istrovstvÃŃ
    0.07
     update
    0.07
    illac
    0.07
     Updates
    0.07
    atten
    0.07
    Activations Density 0.014%

    No Known Activations