© 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 EvalsExportsAPI 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. 56236
    Prev
    Next
    INDEX
    Explanations

    logical assertions and conclusions regarding mathematical proofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Common conjunction words, punctuation marks, and structural elements that connect clauses, introduce conditions, or organize content in formal or technical writing.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ëĿ½
    -0.06
    Disappear
    -0.06
    Verb
    -0.06
    ibox
    -0.06
    etter
    -0.06
    742
    -0.06
     Semaphore
    -0.06
    ẽ
    -0.06
    _Style
    -0.06
    intree
    -0.06
    POSITIVE LOGITS
    aran
    0.07
    osi
    0.07
    ogle
    0.06
     molec
    0.06
    ollow
    0.06
     hers
    0.06
    éĥ½æĺ¯
    0.06
    оген
    0.06
    classed
    0.06
     turno
    0.06
    Activations Density 0.028%

    No Known Activations