© 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. 83282
    Prev
    Next
    INDEX
    Explanations

    categories or labels associated with different types of content

    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
    ubl
    -0.07
     Král
    -0.07
    Ñħо
    -0.06
    .ValidationError
    -0.06
    åĴ¨
    -0.06
    osi
    -0.06
    achen
    -0.06
    RIX
    -0.06
    ÑĸÑģÑĤ
    -0.06
     Zu
    -0.06
    POSITIVE LOGITS
     tier
    0.07
    rama
    0.06
    kontakte
    0.06
    elif
    0.06
    anny
    0.06
    getc
    0.06
     jq
    0.06
    esteem
    0.05
     Tier
    0.05
     frec
    0.05
    Activations Density 0.004%

    No Known Activations