© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95718
    Prev
    Next
    INDEX
    Explanations

    references to geographical or spatial concepts

    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
    tember
    -0.07
    utzer
    -0.07
    aju
    -0.07
    تز
    -0.07
    orough
    -0.07
    ynet
    -0.07
    око
    -0.06
    zeÅĦ
    -0.06
    rale
    -0.06
    icer
    -0.06
    POSITIVE LOGITS
     Vit
    0.06
    ashi
    0.06
     realloc
    0.06
    leans
    0.06
     Kov
    0.05
    ih
    0.05
    atem
    0.05
     Rocket
    0.05
     Hawkins
    0.05
    ubs
    0.05
    Activations Density 0.000%

    No Known Activations