© 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. 77473
    Prev
    Next
    INDEX
    Explanations

    concepts associated with rules, strategies, and underlying principles in various contexts

    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
    ãģijãĤĮãģ°
    -0.07
    á»
    -0.07
    isia
    -0.07
    whose
    -0.07
    ç
    -0.07
    theless
    -0.06
    ########################################################
    -0.06
    ameda
    -0.06
    .Undef
    -0.06
    roy
    -0.06
    POSITIVE LOGITS
    ä¹ĭä¸Ģ
    0.07
    /question
    0.07
    .ht
    0.07
    oins
    0.06
    _CBC
    0.06
    obo
    0.06
     Moff
    0.06
     Hart
    0.06
    umb
    0.06
    ograd
    0.06
    Activations Density 0.059%

    No Known Activations