© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 91836
    Prev
    Next
    INDEX
    Explanations

    HTML tags and attributes related to language specifications

    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
    alcon
    -0.09
    ãĤº
    -0.08
    $MESS
    -0.08
    berman
    -0.07
    inner
    -0.07
    atomy
    -0.07
    owie
    -0.07
    escal
    -0.06
     Inner
    -0.06
    -inner
    -0.06
    POSITIVE LOGITS
    rell
    0.06
    ãĥ©ãĤ¹
    0.06
    ria
    0.06
    ecies
    0.06
    214
    0.06
    tip
    0.05
    è¾°
    0.05
    eh
    0.05
    loy
    0.05
    Tip
    0.05
    Activations Density 0.000%

    No Known Activations