© 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. 95179
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "In" at the beginning of sentences or phrases

    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
    stk
    -0.07
    grily
    -0.07
     notamment
    -0.07
    ec
    -0.07
    plemented
    -0.07
    qd
    -0.06
    견
    -0.06
    entric
    -0.06
    culate
    -0.06
    ecome
    -0.06
    POSITIVE LOGITS
     overall
    0.07
    adays
    0.07
    orda
    0.06
    cheon
    0.06
     regards
    0.06
    aal
    0.06
    flate
    0.06
     actual
    0.06
    agi
    0.06
    alach
    0.06
    Activations Density 0.040%

    No Known Activations