© 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. 40699
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting symbols in a document

    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
    xing
    -0.07
    kop
    -0.07
    ·
    -0.07
    å¸Į
    -0.07
    imiter
    -0.07
    audi
    -0.07
    arah
    -0.07
    PreparedStatement
    -0.06
     Hydra
    -0.06
    imi
    -0.06
    POSITIVE LOGITS
    enin
    0.06
    ufe
    0.06
    ore
    0.06
     Wenger
    0.06
     Bali
    0.06
    //=
    0.06
     refined
    0.05
    ائÙģ
    0.05
    zew
    0.05
    ãĢĤãģĿãģĹãģ¦
    0.05
    Activations Density 0.009%

    No Known Activations