© 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. 15-LLAMASCOPE-RES-131K
    11. 930
    Prev
    Next
    INDEX
    Explanations

    occurrences of significant action verbs or phrases that indicate an event or a demand for attention

    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
    edia
    -0.06
    edar
    -0.06
    iese
    -0.06
    vido
    -0.06
     bitmask
    -0.06
    itelist
    -0.06
    IVO
    -0.06
    UMP
    -0.06
    enthal
    -0.06
    bjerg
    -0.06
    POSITIVE LOGITS
    fik
    0.08
    eci
    0.07
    ãĥ¼ãĥ«
    0.07
    &s
    0.07
    olik
    0.07
    yp
    0.06
    ÑĥнкÑĤ
    0.06
    TestFixture
    0.06
    Translated
    0.06
     summ
    0.06
    Activations Density 0.036%

    No Known Activations