© 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. 76168
    Prev
    Next
    INDEX
    Explanations

    phrases related to offering recommendations or critiques of books

    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
     Hayward
    -0.07
    partment
    -0.06
     Mov
    -0.06
    ilm
    -0.06
    abilia
    -0.06
     Glob
    -0.06
    legates
    -0.06
    åĢī
    -0.05
    곡
    -0.05
    æĶ¯
    -0.05
    POSITIVE LOGITS
     novel
    0.13
     novels
    0.11
     Novel
    0.10
     book
    0.09
     author
    0.09
    nov
    0.09
     books
    0.09
     audi
    0.08
     Author
    0.08
    .dm
    0.08
    Activations Density 0.534%

    No Known Activations