© 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. 84688
    Prev
    Next
    INDEX
    Explanations

    references to crime, investigations, and varying narratives surrounding events

    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
    556
    -0.07
    licer
    -0.07
     Leban
    -0.07
    avit
    -0.07
    anio
    -0.07
    igit
    -0.07
    æľŁ
    -0.07
    anth
    -0.07
    jos
    -0.07
    orsk
    -0.07
    POSITIVE LOGITS
     events
    0.10
    events
    0.08
     Events
    0.08
     details
    0.08
    Events
    0.08
    äºĭ件
    0.07
     circumstances
    0.07
     event
    0.07
    Details
    0.07
    -events
    0.07
    Activations Density 0.022%

    No Known Activations