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. 9-LLAMASCOPE-RES-131K
    6. 95753
    Prev
    Next
    INDEX
    Explanations

    ISBN numbers and related identifiers

    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
    asto
    -0.06
     existence
    -0.06
     w
    -0.06
    luv
    -0.06
     Carroll
    -0.05
    ssf
    -0.05
     Holmes
    -0.05
    PLEX
    -0.05
    öst
    -0.05
    lide
    -0.05
    POSITIVE LOGITS
    ÑĪÑĥ
    0.08
    uja
    0.07
    oldur
    0.07
    [Unit
    0.07
    uards
    0.07
    ippet
    0.07
    omatic
    0.07
     Conc
    0.07
    elop
    0.07
    sian
    0.07
    Activations Density 0.000%

    No Known Activations