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. 96189
    Prev
    Next
    INDEX
    Explanations

    fragments or syllables commonly associated with various types of actions or objects

    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
    rowable
    -0.08
    errupted
    -0.08
    ügen
    -0.08
    @qq
    -0.07
    аÑĢод
    -0.07
    رش
    -0.07
    cej
    -0.07
    oulos
    -0.07
    utin
    -0.07
    รส
    -0.07
    POSITIVE LOGITS
     Vict
    0.07
    insky
    0.07
    Ĺ
    0.06
    odes
    0.06
    amarin
    0.06
    elta
    0.06
    amo
    0.06
    abase
    0.06
     Lambert
    0.06
    GLE
    0.06
    Activations Density 0.124%

    No Known Activations