© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82557
    Prev
    Next
    INDEX
    Explanations

    expressions of future potential or 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
    clamation
    -0.07
    idon
    -0.07
    ood
    -0.06
    اÙĩ
    -0.06
    urs
    -0.06
    ria
    -0.06
    eval
    -0.06
    ez
    -0.06
    illon
    -0.06
    rels
    -0.06
    POSITIVE LOGITS
    kommen
    0.12
    iams
    0.08
    ingly
    0.08
    ough
    0.08
    slaught
    0.07
    power
    0.07
    fully
    0.07
    airo
    0.07
    igg
    0.07
    iston
    0.07
    Activations Density 0.010%

    No Known Activations