© 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. 116629
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue and interactions within narratives

    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
    andon
    -0.07
    cheng
    -0.07
    itsu
    -0.07
    olf
    -0.06
    ulos
    -0.06
    ánt
    -0.06
    zel
    -0.06
     viewers
    -0.06
    loser
    -0.06
    contenido
    -0.06
    POSITIVE LOGITS
     somebody
    0.11
     someone
    0.11
    someone
    0.10
     these
    0.09
     them
    0.08
    these
    0.08
     alguien
    0.08
    è¿ĻäºĽ
    0.08
     tÄĽchto
    0.07
    éĤ£äºĽ
    0.07
    Activations Density 0.026%

    No Known Activations