Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 84207
    Prev
    Next
    INDEX
    Explanations

    words associated with forward-looking or anticipatory concepts

    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
    uran
    -0.08
     recycle
    -0.07
    æ
    -0.07
    iphy
    -0.07
    Åĺ
    -0.07
    isure
    -0.07
    ãn
    -0.07
    asant
    -0.07
    cth
    -0.07
    .tell
    -0.07
    POSITIVE LOGITS
    ingham
    0.06
     Ary
    0.06
    atted
    0.06
     promotion
    0.06
    raman
    0.06
    Mob
    0.05
    rve
    0.05
     throat
    0.05
    otine
    0.05
     Understand
    0.05
    Activations Density 0.002%

    No Known Activations