© 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. 15-LLAMASCOPE-RES-131K
    11. 104075
    Prev
    Next
    INDEX
    Explanations

    language related to predictions and assumptions about future events

    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
    úa
    -0.07
    enas
    -0.07
    ãĥ¼ãĥijãĥ¼
    -0.07
    peria
    -0.07
    ataka
    -0.07
    avez
    -0.07
    ÑĦÑĤ
    -0.07
    esini
    -0.07
    æ¡£
    -0.07
     Content
    -0.06
    POSITIVE LOGITS
     history
    0.06
     Compound
    0.06
     past
    0.06
    رب
    0.06
     continuation
    0.06
    èį·
    0.06
    Compound
    0.06
    è¡
    0.06
    ason
    0.06
     compound
    0.06
    Activations Density 0.012%

    No Known Activations