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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4799
    Prev
    Next
    INDEX
    Explanations

    references to programming code or syntax elements related to AWS services

    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
    reau
    -0.06
    PRS
    -0.06
    unting
    -0.06
    ÑĢÑĮ
    -0.06
    voy
    -0.06
     Sext
    -0.05
    iare
    -0.05
    Äħd
    -0.05
    iar
    -0.05
    arence
    -0.05
    POSITIVE LOGITS
     rub
    0.09
    nodoc
    0.08
    OffsetTable
    0.07
    olle
    0.07
    olis
    0.07
    ãĤ
    0.07
    /GPL
    0.07
     polov
    0.07
    .styleable
    0.07
    deaux
    0.07
    Activations Density 0.004%

    No Known Activations