© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126351
    Prev
    Next
    INDEX
    Explanations

    references to watching television and movies

    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
    ambre
    -0.08
    .DropTable
    -0.08
    á»įng
    -0.07
    коÑĤ
    -0.07
    ần
    -0.07
    _EVT
    -0.07
    ynch
    -0.07
    Shot
    -0.07
    SHOT
    -0.07
    celik
    -0.07
    POSITIVE LOGITS
     movies
    0.10
     rer
    0.09
     television
    0.08
     movie
    0.08
     Rug
    0.07
     TV
    0.07
     watching
    0.07
     cartoons
    0.07
     football
    0.07
     Movies
    0.07
    Activations Density 0.040%

    No Known Activations