© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 129029
    Prev
    Next
    INDEX
    Explanations

    questions posed in the text

    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
    .scalablytyped
    -0.07
    (#)
    -0.07
    eck
    -0.07
    ÑĢап
    -0.07
    etten
    -0.07
    bedo
    -0.07
    ebe
    -0.07
    CK
    -0.07
    uraa
    -0.07
    ÑģÑĤи
    -0.07
    POSITIVE LOGITS
    coma
    0.06
     around
    0.06
    around
    0.06
    -around
    0.06
     Around
    0.06
    ToLocal
    0.06
     ghost
    0.06
     does
    0.06
    opup
    0.05
    ask
    0.05
    Activations Density 0.000%

    No Known Activations