© 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. 15-LLAMASCOPE-RES-131K
    11. 103870
    Prev
    Next
    INDEX
    Explanations

    locations and spatial descriptions in the text

    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
    lesi
    -0.07
    hoff
    -0.06
    adb
    -0.06
    memberof
    -0.06
     lil
    -0.06
    ADED
    -0.06
     coverage
    -0.06
    yg
    -0.05
    aad
    -0.05
    coon
    -0.05
    POSITIVE LOGITS
    ÑĢиз
    0.07
    edeki
    0.07
    urs
    0.07
    üzel
    0.07
    ingle
    0.07
    <context
    0.07
    usunda
    0.07
    790
    0.07
    itle
    0.06
    HLT
    0.06
    Activations Density 0.017%

    No Known Activations