© 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. 29570
    Prev
    Next
    INDEX
    Explanations

    terms related to cropping and modification in images and potentially in agricultural contexts

    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
    quam
    -0.07
    ives
    -0.07
    IAL
    -0.06
    PRI
    -0.06
    .normalize
    -0.06
    antas
    -0.06
    bol
    -0.06
    room
    -0.06
     opposite
    -0.06
    uali
    -0.06
    POSITIVE LOGITS
    acia
    0.07
    urgeon
    0.07
    ajaran
    0.07
    chia
    0.07
    sey
    0.07
    dü
    0.07
    peria
    0.07
    acias
    0.06
    anium
    0.06
    emer
    0.06
    Activations Density 0.003%

    No Known Activations