© 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. 15-LLAMASCOPE-RES-131K
    11. 86218
    Prev
    Next
    INDEX
    Explanations

    phrases related to the absence and presence of certain conditions or actions

    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
    ears
    -0.07
    имÑĥ
    -0.06
    á»įc
    -0.06
    arkin
    -0.06
    pose
    -0.06
    ger
    -0.06
    idl
    -0.06
    eldon
    -0.06
    .locals
    -0.06
     EAR
    -0.06
    POSITIVE LOGITS
     except
    0.11
    except
    0.10
     nÃło
    0.10
     ever
    0.07
     any
    0.07
     anywhere
    0.07
     either
    0.07
    Except
    0.07
     Except
    0.07
     EITHER
    0.07
    Activations Density 0.025%

    No Known Activations