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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5196
    Prev
    Next
    INDEX
    Explanations

    terms related to predictions and projections

    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
    rena
    -0.08
    aga
    -0.08
    anki
    -0.07
    aug
    -0.07
    -thirds
    -0.07
    ko
    -0.07
    kt
    -0.07
    è´¨
    -0.06
     Graz
    -0.06
    allel
    -0.06
    POSITIVE LOGITS
    ers
    0.15
    ed
    0.13
    ÂŃing
    0.08
    edly
    0.08
    ability
    0.08
    owanie
    0.08
    edImage
    0.08
    ing
    0.08
    ERS
    0.07
    íĮħ
    0.07
    Activations Density 0.004%

    No Known Activations