© 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. 57077
    Prev
    Next
    INDEX
    Explanations

    details related to geographical features and structures

    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
    037
    -0.06
    .volley
    -0.06
    ĶåĽŀ
    -0.06
     áº
    -0.06
    .fs
    -0.06
    mtree
    -0.06
     Pip
    -0.06
     Bust
    -0.06
     penet
    -0.06
    aines
    -0.06
    POSITIVE LOGITS
     bridge
    0.10
     bridges
    0.08
     steel
    0.08
     deck
    0.08
    steel
    0.08
     Bridge
    0.08
    .struct
    0.07
    bridge
    0.07
     brid
    0.07
    æ¡¥
    0.07
    Activations Density 0.016%

    No Known Activations