© 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. 3223
    Prev
    Next
    INDEX
    Explanations

    patterns in import/export codes or numerical identifiers related to various communications devices

    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
    kas
    -0.06
    geme
    -0.06
    ear
    -0.06
    Extra
    -0.06
    opes
    -0.06
    ra
    -0.06
    rr
    -0.06
    ote
    -0.06
    åĮº
    -0.05
    ç²
    -0.05
    POSITIVE LOGITS
    adol
    0.09
    ulen
    0.08
    eshire
    0.07
    igsaw
    0.07
    @qq
    0.07
    leground
    0.07
    evice
    0.07
    onis
    0.07
    olan
    0.06
    .codec
    0.06
    Activations Density 0.115%

    No Known Activations