© 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. 119449
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components in coding

    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
    oley
    -0.07
    niž
    -0.07
    sov
    -0.07
    ãĢ
    -0.07
    ãĥ«ãĥĪ
    -0.07
    /Dk
    -0.07
    cÃŃ
    -0.07
    Ghost
    -0.07
    èıľ
    -0.06
    orthand
    -0.06
    POSITIVE LOGITS
    umb
    0.07
     Dit
    0.06
    ter
    0.06
     sahip
    0.06
    amo
    0.06
    FILE
    0.06
    ty
    0.06
    ìĪľ
    0.06
    ifa
    0.05
    antar
    0.05
    Activations Density 0.000%

    No Known Activations