© 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. 17-LLAMASCOPE-RES-131K
    11. 15754
    Prev
    Next
    INDEX
    Explanations

    quantities and counts related to applications or requirements

    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
    ázd
    -0.08
    sis
    -0.08
    emek
    -0.07
    rys
    -0.07
     Lid
    -0.07
    Ïĥκε
    -0.07
     hete
    -0.07
    Ħĸ
    -0.07
    ober
    -0.07
    ilis
    -0.07
    POSITIVE LOGITS
     Bord
    0.06
     randomly
    0.06
     or
    0.06
    urr
    0.06
    ach
    0.05
     mutually
    0.05
     cre
    0.05
    048
    0.05
    ans
    0.05
     (
    0.05
    Activations Density 0.034%

    No Known Activations