© 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. 76227
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to categorization and submission of creative works

    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
    qd
    -0.07
    éru
    -0.07
    atron
    -0.06
    νÏİ
    -0.06
    ornings
    -0.06
    afen
    -0.06
    SSF
    -0.06
    Codec
    -0.06
    fad
    -0.06
    ial
    -0.06
    POSITIVE LOGITS
    ksam
    0.07
    utsche
    0.07
     permalink
    0.07
    åĶ¯
    0.07
    ptide
    0.07
     tags
    0.06
    plet
    0.06
     suppressed
    0.06
    .createComponent
    0.06
    _HIT
    0.06
    Activations Density 0.001%

    No Known Activations