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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96109
    Prev
    Next
    INDEX
    Explanations

    sequences of events in a game or performance

    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
    ovit
    -0.07
    stadt
    -0.07
    auce
    -0.06
    Äįit
    -0.06
    umeric
    -0.06
    umbo
    -0.06
    andr
    -0.06
    ville
    -0.06
    spell
    -0.06
    ivos
    -0.06
    POSITIVE LOGITS
    atology
    0.06
    .RELATED
    0.06
     hor
    0.06
    dz
    0.06
    (fid
    0.06
    oru
    0.06
     Pratt
    0.06
    .MON
    0.06
    apo
    0.06
    OffsetTable
    0.06
    Activations Density 0.004%

    No Known Activations