© 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. 28000
    Prev
    Next
    INDEX
    Explanations

    quantitative data and numerical information related to organizations and events

    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
    ÅĻad
    -0.08
    swick
    -0.07
    CLUD
    -0.07
    áž
    -0.06
    ãģ°ãģĭãĤĬ
    -0.06
    ulan
    -0.06
     closest
    -0.06
    eln
    -0.06
    egend
    -0.06
    æ®Ĭ
    -0.06
    POSITIVE LOGITS
     additional
    0.26
     another
    0.24
     further
    0.22
    additional
    0.22
    another
    0.21
     Additional
    0.20
     weitere
    0.19
    Additional
    0.19
     thêm
    0.19
     Another
    0.18
    Activations Density 0.102%

    No Known Activations