Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 74954
    Prev
    Next
    INDEX
    Explanations

    settings and features related to homes and properties

    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
    okens
    -0.07
    WithMany
    -0.06
    utom
    -0.06
    .Helper
    -0.06
    ossal
    -0.06
    oller
    -0.06
    abouts
    -0.06
    usan
    -0.05
    ADF
    -0.05
    aki
    -0.05
    POSITIVE LOGITS
     intact
    0.07
    angep
    0.07
    _builtin
    0.06
    stery
    0.06
    $MESS
    0.06
    thrown
    0.06
    attached
    0.06
     Capability
    0.06
    GetObject
    0.06
    enment
    0.06
    Activations Density 0.063%

    No Known Activations