© 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. 9-LLAMASCOPE-RES-131K
    11. 95602
    Prev
    Next
    INDEX
    Explanations

    terms related to legal documentation and processes

    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
    rame
    -0.07
    stroy
    -0.06
    ipsis
    -0.06
    .masks
    -0.06
    ::-
    -0.06
     Height
    -0.06
     åº
    -0.06
    oven
    -0.06
    IMIT
    -0.06
     Cop
    -0.06
    POSITIVE LOGITS
    éĶĭ
    0.06
     patron
    0.06
    ware
    0.06
    Ńå·ŀ
    0.06
    offer
    0.06
    ubble
    0.06
    UU
    0.06
     Corrections
    0.06
    nger
    0.05
    igan
    0.05
    Activations Density 0.001%

    No Known Activations