© 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. 18312
    Prev
    Next
    INDEX
    Explanations

    specific references to episodes and corrections in a podcast or media context

    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
    anes
    -0.07
    rms
    -0.07
    onian
    -0.07
    adder
    -0.06
    OfClass
    -0.06
    choice
    -0.06
    SizeMode
    -0.06
    ilian
    -0.06
    à¤ł
    -0.06
    ajan
    -0.06
    POSITIVE LOGITS
    (s
    0.08
     actionTypes
    0.07
     reason
    0.07
     problem
    0.07
    åħ·ä½ĵ
    0.07
    usalem
    0.07
    åİŁåĽł
    0.06
    aina
    0.06
     exactly
    0.06
    .problem
    0.06
    Activations Density 0.025%

    No Known Activations