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. 57439
    Prev
    Next
    INDEX
    Explanations

    references to family dynamics and children's experiences

    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
     Bride
    -0.07
    ICAST
    -0.07
    cox
    -0.06
    ROTO
    -0.06
    ÂŃs
    -0.06
    innen
    -0.06
    agra
    -0.06
    ubber
    -0.06
     fractions
    -0.06
    ICODE
    -0.06
    POSITIVE LOGITS
    atz
    0.07
    oot
    0.07
     dil
    0.06
    onom
    0.06
    untime
    0.06
    ubat
    0.06
    ahan
    0.06
    olu
    0.06
     custody
    0.06
    indle
    0.06
    Activations Density 0.007%

    No Known Activations