© 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. 3271
    Prev
    Next
    INDEX
    Explanations

    concepts related to storytelling and narratives, particularly in a collaborative or team context

    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
    werk
    -0.08
    okt
    -0.07
    wer
    -0.06
    WER
    -0.06
    engin
    -0.06
     Bradley
    -0.06
     reverse
    -0.06
     Morrow
    -0.06
    гал
    -0.06
     Reverse
    -0.06
    POSITIVE LOGITS
    :
    0.13
    ा:
    0.08
    *:
    0.08
    ï¼ļ
    0.08
    à¹Į:
    0.07
    ():
    0.07
     <!--[
    0.07
    odied
    0.06
     STDCALL
    0.06
    avir
    0.06
    Activations Density 0.073%

    No Known Activations