© 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. 71448
    Prev
    Next
    INDEX
    Explanations

    elements related to programming syntax

    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
    utsch
    -0.07
     ìĹŃìĭľ
    -0.07
    pbs
    -0.06
    _ALLOW
    -0.06
    .Appearance
    -0.06
    ÙĬع
    -0.06
    rott
    -0.06
    emap
    -0.06
    assin
    -0.06
    pill
    -0.06
    POSITIVE LOGITS
    enko
    0.06
    esda
    0.06
    ãĤĪãĤĬãĤĤ
    0.06
    jiang
    0.06
    lek
    0.05
    folk
    0.05
    _equalTo
    0.05
    Å¡k
    0.05
    allel
    0.05
    ellaneous
    0.05
    Activations Density 0.000%

    No Known Activations