© 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. 71060
    Prev
    Next
    INDEX
    Explanations

    expressions of possibility, uncertainty, and inquiries about procedures or solutions

    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
    rar
    -0.06
    asca
    -0.06
    emy
    -0.06
    .ManyToMany
    -0.06
    оÑĤоÑĢ
    -0.06
    ãĥ³ãĥĸ
    -0.06
    मन
    -0.06
     interests
    -0.06
    qus
    -0.06
    ë£
    -0.06
    POSITIVE LOGITS
     how
    0.10
     How
    0.08
    onical
    0.08
    how
    0.08
    å¦Ĥä½ķ
    0.08
    How
    0.07
    -how
    0.07
     Am
    0.07
     why
    0.07
    akah
    0.07
    Activations Density 0.004%

    No Known Activations