© 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. 93506
    Prev
    Next
    INDEX
    Explanations

    references to locations, particularly cities and states, as well as contextual identifiers related to events

    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
     Brief
    -0.06
    un
    -0.06
    riter
    -0.06
     Ø°
    -0.06
    uen
    -0.06
    -0.06
     Rim
    -0.06
    -
    -0.06
     Lac
    -0.06
    anim
    -0.06
    POSITIVE LOGITS
    /stdc
    0.08
    .UIManager
    0.07
    kazy
    0.07
    eriod
    0.07
    engin
    0.07
    pillar
    0.07
    è°±
    0.07
    Uvs
    0.07
    골
    0.07
    tlement
    0.07
    Activations Density 0.004%

    No Known Activations