© 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. 17-LLAMASCOPE-RES-131K
    6. 125375
    Prev
    Next
    INDEX
    Explanations

    elements related to medical conditions and treatments

    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
     super
    -0.06
    **
    -0.06
     Vic
    -0.06
    rella
    -0.06
     playground
    -0.06
     Adler
    -0.05
    .pack
    -0.05
     Be
    -0.05
    ahir
    -0.05
    ippo
    -0.05
    POSITIVE LOGITS
    nnen
    0.09
    (åľŁ
    0.08
    kili
    0.08
    longleftrightarrow
    0.08
    _Lean
    0.08
    itti
    0.08
    CLOCKS
    0.07
    .ncbi
    0.07
    UTILITY
    0.07
    resi
    0.07
    Activations Density 0.074%

    No Known Activations