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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 89626
    Prev
    Next
    INDEX
    Explanations

    inquiries about the feasibility or reasonableness of approaches or designs

    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
    .scalablytyped
    -0.07
    pector
    -0.07
    yaw
    -0.06
    mayan
    -0.06
    ÑĤÑĢа
    -0.06
     Roch
    -0.06
    atted
    -0.06
    Verbose
    -0.06
     impossible
    -0.06
    nete
    -0.06
    POSITIVE LOGITS
     correctness
    0.08
     correct
    0.08
    uters
    0.07
     ли
    0.07
    ulis
    0.07
    ť
    0.07
    onth
    0.07
    orsi
    0.07
    ihar
    0.07
     appropri
    0.06
    Activations Density 0.005%

    No Known Activations