Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 16443
    Prev
    Next
    INDEX
    Explanations

    programming-related terms or functions

    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
    isse
    -0.07
    lop
    -0.07
    imes
    -0.06
    ej
    -0.06
    hatt
    -0.06
    ByExample
    -0.06
    fono
    -0.06
    İL
    -0.06
    CAC
    -0.06
    ghan
    -0.06
    POSITIVE LOGITS
     Destructor
    0.07
    agher
    0.06
    oso
    0.06
     voksne
    0.06
    æ¯
    0.06
    bsites
    0.06
     getLogger
    0.06
     sebe
    0.06
    ceipt
    0.06
    icorn
    0.06
    Activations Density 0.004%

    No Known Activations