© 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. 3909
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to patient medical details and assessments

    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
    chet
    -0.08
     å¹
    -0.06
     Brit
    -0.06
     kde
    -0.06
    me
    -0.06
     Like
    -0.06
     Innoc
    -0.06
     —
    -0.06
    u
    -0.05
     like
    -0.05
    POSITIVE LOGITS
    Ã¤ÃŁ
    0.08
    êt
    0.07
    WithMany
    0.07
    chema
    0.07
    icens
    0.07
    ÏĥÏĩ
    0.07
    Äįel
    0.07
    ewire
    0.07
    NSUserDefaults
    0.07
    /stdc
    0.07
    Activations Density 0.001%

    No Known Activations