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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77169
    Prev
    Next
    INDEX
    Explanations

    conjunctions or transitional phrases indicating contrast or condition

    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
    ullan
    -0.08
    ieres
    -0.07
    vl
    -0.07
    sciously
    -0.07
    ieren
    -0.07
    çͳåįļ
    -0.07
    .UnitTesting
    -0.07
    vik
    -0.07
    _parms
    -0.07
    chts
    -0.07
    POSITIVE LOGITS
    s
    0.10
     there
    0.10
    some
    0.08
    there
    0.08
     many
    0.07
    d
    0.07
     overall
    0.07
    utow
    0.07
     no
    0.07
    doi
    0.07
    Activations Density 0.031%

    No Known Activations