© 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. 55808
    Prev
    Next
    INDEX
    Explanations

    terms related to medical diagnosis and analysis of pathological conditions

    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
     occasion
    -0.07
    _IND
    -0.06
     Pere
    -0.06
    ÙĬتÙĬ
    -0.06
    agan
    -0.06
     piece
    -0.06
     facil
    -0.06
    cela
    -0.05
     zipcode
    -0.05
    055
    -0.05
    POSITIVE LOGITS
    idar
    0.08
    arty
    0.08
    /stdc
    0.07
    ãĥ¼ãĥ
    0.07
    icut
    0.07
    iband
    0.07
    contres
    0.07
    COVID
    0.07
    swick
    0.06
    çıŃ
    0.06
    Activations Density 0.040%

    No Known Activations