© 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. 76678
    Prev
    Next
    INDEX
    Explanations

    references to human beings and social interactions

    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
    lev
    -0.07
    .openg
    -0.07
    PN
    -0.07
    enberg
    -0.06
    lech
    -0.06
    mul
    -0.06
     Simpl
    -0.06
    wards
    -0.06
    iner
    -0.06
    ONENT
    -0.06
    POSITIVE LOGITS
     who
    0.08
    æ²¢
    0.07
    cker
    0.06
    thy
    0.06
    AIT
    0.06
    reau
    0.06
    ÏĦÏİ
    0.06
     MOST
    0.06
     chứ
    0.06
    abox
    0.06
    Activations Density 0.015%

    No Known Activations