© 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. 106937
    Prev
    Next
    INDEX
    Explanations

    references and links related to historical figures and 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
    ela
    -0.06
     mans
    -0.06
    497
    -0.06
    741
    -0.06
     Beg
    -0.05
    ĸ
    -0.05
    plier
    -0.05
    SS
    -0.05
    claimer
    -0.05
    çĶ²
    -0.05
    POSITIVE LOGITS
    _stub
    0.08
     official
    0.08
     oficial
    0.07
     ENTRY
    0.07
    ï¼ĮåŃĺäºİ
    0.07
    Arch
    0.07
    Stub
    0.07
    ENTRY
    0.07
    .il
    0.07
    âĨij
    0.07
    Activations Density 0.007%

    No Known Activations