© 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. 9-LLAMASCOPE-RES-131K
    11. 98655
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical attributes or features

    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
    asso
    -0.07
    iaux
    -0.07
    reh
    -0.07
    hod
    -0.06
    浦
    -0.06
    phia
    -0.06
     Pearce
    -0.06
    ellular
    -0.06
    stalk
    -0.06
    Ban
    -0.06
    POSITIVE LOGITS
    eba
    0.07
     Herc
    0.06
    xec
    0.06
    _mime
    0.06
     Qed
    0.05
    길
    0.05
    rence
    0.05
    reff
    0.05
     Portions
    0.05
    γει
    0.05
    Activations Density 0.024%

    No Known Activations