© 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. 15-LLAMASCOPE-RES-131K
    11. 27215
    Prev
    Next
    INDEX
    Explanations

    phrases related to artistic interpretation and classification challenges

    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
    ud
    -0.07
    ibal
    -0.07
    elman
    -0.07
    quist
    -0.06
    avs
    -0.06
    .mo
    -0.06
    ahl
    -0.06
    iset
    -0.06
    iec
    -0.06
     иÑģÑħод
    -0.06
    POSITIVE LOGITS
    oogle
    0.07
    acket
    0.07
     descri
    0.07
     describe
    0.07
     description
    0.07
     conventional
    0.07
     exact
    0.07
     describing
    0.07
    qua
    0.06
    escription
    0.06
    Activations Density 0.023%

    No Known Activations