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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 96129
    Prev
    Next
    INDEX
    Explanations

    names of individuals associated with geologic maps

    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
    ather
    -0.08
    elman
    -0.07
    hurst
    -0.07
    Ãłm
    -0.07
     replay
    -0.06
    smith
    -0.06
    lich
    -0.06
    PRS
    -0.06
    iar
    -0.06
    airy
    -0.06
    POSITIVE LOGITS
    .native
    0.07
     Directions
    0.07
    .idea
    0.07
    -handle
    0.06
    aklı
    0.06
    irection
    0.06
    handles
    0.06
    лаг
    0.06
     momentos
    0.06
    auga
    0.06
    Activations Density 0.027%

    No Known Activations