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. 95860
    Prev
    Next
    INDEX
    Explanations

    word roots and prefixes related to various actions and 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
    rouch
    -0.08
    ernetes
    -0.08
    ptions
    -0.08
    lád
    -0.07
    vangst
    -0.07
    ÑĦек
    -0.07
    dbuf
    -0.07
    lparr
    -0.07
    пÑĤом
    -0.07
    алог
    -0.07
    POSITIVE LOGITS
    ed
    0.12
    ly
    0.10
    Ø©
    0.07
    ت
    0.07
    ÑģÑı
    0.06
    çij
    0.06
    त
    0.06
    gether
    0.06
    enment
    0.06
    edBy
    0.06
    Activations Density 0.110%

    No Known Activations