© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 86624
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" and related prepositions within the text

    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
    .sk
    -0.07
    arde
    -0.07
    ackers
    -0.07
    ãĥĸãĥ«
    -0.06
    ieren
    -0.06
    ãĥ¼ãĥĸ
    -0.06
    ãĥ¼ãĥĦ
    -0.06
    ichert
    -0.06
    aru
    -0.06
    rong
    -0.06
    POSITIVE LOGITS
    odyn
    0.08
    abi
    0.06
     effort
    0.06
     thang
    0.06
     Abs
    0.06
    endi
    0.06
    ABS
    0.06
     absence
    0.06
    ATAR
    0.06
     ord
    0.06
    Activations Density 0.055%

    No Known Activations