© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 129143
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and logical proofs

    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
    omik
    -0.08
    Äįit
    -0.08
    REFERRED
    -0.08
    NullOr
    -0.08
    ucch
    -0.08
     ngang
    -0.08
    ãĤ«ãĥ¼
    -0.08
    leftright
    -0.08
    itest
    -0.08
    _None
    -0.08
    POSITIVE LOGITS
     somewhere
    0.12
     there
    0.09
     somebody
    0.08
     SOM
    0.08
     someone
    0.08
     always
    0.08
     There
    0.08
     find
    0.07
    there
    0.07
     Find
    0.07
    Activations Density 0.187%

    No Known Activations