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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 70026
    Prev
    Next
    INDEX
    Explanations

    references to player impact and team dynamics

    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
    .openConnection
    -0.07
     nghiá»ĩp
    -0.07
    NB
    -0.07
    LEM
    -0.06
    lems
    -0.06
     Lands
    -0.06
    eday
    -0.06
    edn
    -0.06
    NSMutable
    -0.06
    èľ
    -0.06
    POSITIVE LOGITS
     presence
    0.09
     Presence
    0.08
     absence
    0.08
    Presence
    0.07
     addition
    0.07
    presence
    0.07
    _MetaData
    0.07
    adeon
    0.07
    raid
    0.06
    chez
    0.06
    Activations Density 0.025%

    No Known Activations