© 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. 14096
    Prev
    Next
    INDEX
    Explanations

    terms related to legal actions and consequences

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     misunder
    -0.07
    imiz
    -0.06
    enda
    -0.06
    .Qual
    -0.06
    ardon
    -0.06
    cke
    -0.06
    GORITH
    -0.06
    Malloc
    -0.06
    Äįky
    -0.06
    loid
    -0.06
    POSITIVE LOGITS
     any
    0.12
     ANY
    0.10
    any
    0.09
     such
    0.09
     лÑİбой
    0.08
    ä»»ä½ķ
    0.08
     when
    0.07
    Any
    0.07
     anything
    0.07
    -any
    0.07
    Activations Density 0.029%

    No Known Activations