© 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. 57668
    Prev
    Next
    INDEX
    Explanations

    words related to conceptualization or imagination

    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
    prov
    -0.06
     downtown
    -0.06
    Å¡t
    -0.06
    lobals
    -0.06
     â
    -0.06
    GIN
    -0.06
    rab
    -0.05
    kee
    -0.05
    spender
    -0.05
     Hlav
    -0.05
    POSITIVE LOGITS
    imir
    0.07
    ppe
    0.07
    entai
    0.07
    ebin
    0.07
    ocz
    0.07
    opher
    0.07
    вий
    0.07
    Numeric
    0.06
    jte
    0.06
    umeric
    0.06
    Activations Density 0.000%

    No Known Activations