© 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. 17605
    Prev
    Next
    INDEX
    Explanations

    significant names and entities in various contexts

    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
     nues
    -0.08
    âĹİ
    -0.08
    asaki
    -0.08
    bage
    -0.07
    vrier
    -0.07
    anvas
    -0.07
    iston
    -0.07
    iyon
    -0.07
    мени
    -0.07
     اصÙģÙĩ
    -0.07
    POSITIVE LOGITS
     such
    0.16
    such
    0.14
     like
    0.13
    :
    0.10
     including
    0.10
    å¦Ĥ
    0.08
     likes
    0.08
     SUCH
    0.08
     Such
    0.08
     seperti
    0.08
    Activations Density 0.028%

    No Known Activations