© 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. 9-LLAMASCOPE-RES-131K
    11. 94168
    Prev
    Next
    INDEX
    Explanations

    achievements and rankings in competitive contexts

    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
     bars
    -0.06
    bars
    -0.06
     hind
    -0.06
    agini
    -0.05
    ning
    -0.05
     disob
    -0.05
     relation
    -0.05
    .
    -0.05
    inally
    -0.05
    æĥħ
    -0.05
    POSITIVE LOGITS
    dorf
    0.08
    outers
    0.08
    \views
    0.07
    ãģijãĤĮãģ©
    0.07
    Mutable
    0.07
    çak
    0.07
    aset
    0.07
    Outlined
    0.07
    APO
    0.07
    ysize
    0.07
    Activations Density 0.053%

    No Known Activations