© 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. 57639
    Prev
    Next
    INDEX
    Explanations

    strong phrases indicating a desire for guidance or improvement

    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
    hev
    -0.07
    eum
    -0.07
    qw
    -0.07
     either
    -0.06
    ilan
    -0.06
    eker
    -0.06
     IMG
    -0.06
    ika
    -0.06
     or
    -0.06
    NullOrEmpty
    -0.06
    POSITIVE LOGITS
     aforementioned
    0.07
    лик
    0.06
    ãģĸ
    0.06
    ounge
    0.06
    .getAmount
    0.06
    СÐŀ
    0.06
    .Misc
    0.06
    ز
    0.06
    Via
    0.06
    ÑĤап
    0.06
    Activations Density 0.000%

    No Known Activations