© 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. 77048
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate potential outcomes or expectations

    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
     however
    -0.07
    culus
    -0.07
    одо
    -0.07
    peq
    -0.07
    udeau
    -0.07
    ssc
    -0.07
    ãģªãģ®
    -0.07
    Desc
    -0.07
    chten
    -0.07
    adius
    -0.07
    POSITIVE LOGITS
    'll
    0.10
     will
    0.10
    å°±ä¼ļ
    0.09
    will
    0.08
    ä¼ļ
    0.08
    ’ll
    0.08
     sẽ
    0.07
     shall
    0.07
    urma
    0.07
     WILL
    0.07
    Activations Density 0.019%

    No Known Activations