© 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. 120776
    Prev
    Next
    INDEX
    Explanations

    technical terms related to signal processing and conversion

    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
    arging
    -0.06
    @student
    -0.06
     rele
    -0.06
    arus
    -0.06
     depth
    -0.06
    omid
    -0.06
     RAND
    -0.06
    fol
    -0.06
     Gest
    -0.06
    FormattedMessage
    -0.06
    POSITIVE LOGITS
     freq
    0.08
    frequency
    0.08
     frequency
    0.08
    -frequency
    0.08
    freq
    0.08
    Hz
    0.08
    éł»
    0.08
     rate
    0.07
    .freq
    0.07
    é¢ij
    0.07
    Activations Density 0.047%

    No Known Activations