© 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. 76409
    Prev
    Next
    INDEX
    Explanations

    conditional statements and hypothetical scenarios

    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
    unar
    -0.06
    laden
    -0.06
    ãĥ¼ãĥĨ
    -0.06
    emory
    -0.06
     incons
    -0.06
    Wnd
    -0.06
    dorf
    -0.05
    HIR
    -0.05
    urning
    -0.05
     prior
    -0.05
    POSITIVE LOGITS
    ENTS
    0.07
    arah
    0.07
    asd
    0.07
    ãĥ³ãĥĩãĤ£
    0.07
    rames
    0.07
    दर
    0.07
    ãĤ¶ãĥ¼
    0.07
    ovu
    0.07
    uent
    0.06
    zar
    0.06
    Activations Density 0.006%

    No Known Activations