© 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. 117506
    Prev
    Next
    INDEX
    Explanations

    references to academic honors or awards

    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
    álo
    -0.07
     ÐľÑĥ
    -0.07
     unw
    -0.07
    -icons
    -0.06
    \Eloquent
    -0.06
    HEMA
    -0.06
    zsche
    -0.06
    ekk
    -0.06
    impan
    -0.06
    ÐĶÐIJ
    -0.06
    POSITIVE LOGITS
    (SP
    0.07
    以ä¸Ĭ
    0.06
    çĶ³
    0.06
     track
    0.06
    level
    0.06
    644
    0.06
    -level
    0.06
    edList
    0.06
    877
    0.06
    Ïīμα
    0.06
    Activations Density 0.003%

    No Known Activations