© 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. 28977
    Prev
    Next
    INDEX
    Explanations

    instances of hyphenated phrases or expressions related to agreements or partnerships

    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
    asz
    -0.07
    alink
    -0.07
    ocker
    -0.07
    alie
    -0.07
    íݸ
    -0.07
    illisecond
    -0.07
    aling
    -0.07
    onen
    -0.07
    alled
    -0.06
    others
    -0.06
    POSITIVE LOGITS
    reet
    0.07
     Fab
    0.06
    463
    0.06
    tuk
    0.06
    orners
    0.06
    tu
    0.06
    nt
    0.06
    kid
    0.06
     mo
    0.06
    _ENCODING
    0.06
    Activations Density 0.006%

    No Known Activations