© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95634
    Prev
    Next
    INDEX
    Explanations

    instances of fabricated or fictional narratives

    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
    nds
    -0.07
    innie
    -0.07
    monds
    -0.06
    åde
    -0.06
     RuntimeObject
    -0.06
    ¶ģ
    -0.06
    ogh
    -0.06
     Benton
    -0.06
    kees
    -0.06
    nodeName
    -0.06
    POSITIVE LOGITS
    uche
    0.07
    ACES
    0.06
    <*
    0.06
    pus
    0.06
    itious
    0.06
     Zub
    0.06
    gage
    0.06
    crate
    0.06
    .scheme
    0.06
    ENUM
    0.06
    Activations Density 0.014%

    No Known Activations