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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 84019
    Prev
    Next
    INDEX
    Explanations

    instances of emotional vulnerability or personal struggles

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

    Period marks (".") used either at the end of sentences or as part of abbreviations, often serving as content transition points.

    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
    sey
    -0.06
    .RESET
    -0.06
    asa
    -0.06
    enger
    -0.06
    icht
    -0.06
    owa
    -0.06
    iper
    -0.06
    idge
    -0.06
    lah
    -0.06
     ÙĨاØŃ
    -0.06
    POSITIVE LOGITS
    reesome
    0.07
    readcr
    0.07
    udev
    0.07
    ritel
    0.07
    -aos
    0.06
    Schedulers
    0.06
    ublik
    0.06
    ibold
    0.06
    ãĥ³ãĥĶ
    0.06
    ÃĸL
    0.06
    Activations Density 0.180%

    No Known Activations