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. 96152
    Prev
    Next
    INDEX
    Explanations

    HTML and data-related structures in text

    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
     Fro
    -0.07
    anced
    -0.06
    #.
    -0.05
     foul
    -0.05
    datable
    -0.05
    話
    -0.05
    pond
    -0.05
     consolidation
    -0.05
     Decomp
    -0.05
    ivec
    -0.05
    POSITIVE LOGITS
    regor
    0.08
    arry
    0.07
    adden
    0.07
    zem
    0.07
    lsi
    0.07
    orris
    0.07
     Bowman
    0.07
    uar
    0.07
    czy
    0.06
    Ordinal
    0.06
    Activations Density 0.016%

    No Known Activations