© 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. 55863
    Prev
    Next
    INDEX
    Explanations

    terms related to software development, particularly regarding files, modules, and errors

    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
    776
    -0.07
    uke
    -0.07
    peria
    -0.06
    lom
    -0.06
     ^.
    -0.06
    owany
    -0.06
     Orient
    -0.06
    ĵn
    -0.06
    /auto
    -0.06
    ifen
    -0.06
    POSITIVE LOGITS
    (s
    0.07
    factory
    0.06
    MQ
    0.06
    ymbols
    0.06
    MU
    0.06
    QRS
    0.06
    (es
    0.06
     "
    0.06
    splice
    0.06
    ладÑĥ
    0.05
    Activations Density 0.014%

    No Known Activations