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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-LLAMASCOPE-RES-131K
    6. 44193
    Prev
    Next
    INDEX
    Explanations

    phrases expressing determination or resolve

    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
    åĺī
    -0.06
    riere
    -0.06
    ahoma
    -0.06
    AuthProvider
    -0.06
    orsche
    -0.06
    abant
    -0.06
    avez
    -0.06
    orgia
    -0.06
    ureau
    -0.06
    peare
    -0.06
    POSITIVE LOGITS
    ly
    0.19
     to
    0.15
     that
    0.12
     not
    0.11
     NOT
    0.11
     never
    0.11
    to
    0.10
     enough
    0.10
    äºİ
    0.10
    ness
    0.10
    Activations Density 0.006%

    No Known Activations