© 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. 84186
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting related to dialogue or speech

    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
    league
    -0.07
    ÑĦеÑĢ
    -0.07
    703
    -0.06
    odge
    -0.06
     cabo
    -0.06
    maz
    -0.06
    Lights
    -0.06
    errer
    -0.06
     è¡
    -0.06
    .amazonaws
    -0.06
    POSITIVE LOGITS
    tit
    0.08
    اÙĨÙĪÙĨ
    0.07
     Bern
    0.07
    subst
    0.07
     Plate
    0.06
     Rin
    0.06
     plate
    0.06
    adena
    0.06
    .obtain
    0.06
    olean
    0.06
    Activations Density 0.008%

    No Known Activations