© 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. 89958
    Prev
    Next
    INDEX
    Explanations

    names of children or offspring

    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
    Ñģе
    -0.06
    abe
    -0.06
    util
    -0.05
    IDO
    -0.05
    óc
    -0.05
     Les
    -0.05
    alse
    -0.05
    -util
    -0.05
    vore
    -0.05
    sed
    -0.05
    POSITIVE LOGITS
    ÅŁa
    0.08
    ÄŁmen
    0.07
    thus
    0.07
    cilik
    0.07
    @nate
    0.07
    çĿ£
    0.07
    ãĤ«ãĥ«
    0.07
    ä»Ĭå¹´
    0.07
    RunLoop
    0.07
    å¡Ķ
    0.07
    Activations Density 0.014%

    No Known Activations