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. 96159
    Prev
    Next
    INDEX
    Explanations

    expressions related to cultural commentary and the reception of art

    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
    noch
    -0.07
    yer
    -0.07
    iddles
    -0.06
    awy
    -0.06
    eed
    -0.06
    ebb
    -0.06
    .jp
    -0.06
    ROLS
    -0.06
    eger
    -0.06
    ger
    -0.06
    POSITIVE LOGITS
    $MESS
    0.07
    819
    0.06
    cü
    0.06
    λÏĮ
    0.06
    agrant
    0.06
    atego
    0.06
    abant
    0.06
    ufen
    0.06
     //////////////////////////////////////////////////////////////////////////
    0.06
    ogne
    0.06
    Activations Density 0.169%

    No Known Activations