© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 1490
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and dynamics

    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
    bai
    -0.09
     Tate
    -0.08
     Sexo
    -0.08
    ovah
    -0.07
    ÙĦاÙħ
    -0.07
    анка
    -0.07
     Couples
    -0.07
    (æ°´
    -0.07
    veau
    -0.07
    обÑīе
    -0.07
    POSITIVE LOGITS
     step
    0.14
    step
    0.13
     Step
    0.11
    -step
    0.10
     steps
    0.09
    .step
    0.09
    Step
    0.09
    _step
    0.08
    (step
    0.08
     half
    0.08
    Activations Density 0.045%

    No Known Activations