© 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. 81705
    Prev
    Next
    INDEX
    Explanations

    references to links and navigation elements within a digital or web context

    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
    TEGER
    -0.07
    orts
    -0.07
    rve
    -0.07
    ntp
    -0.07
    yla
    -0.07
    rient
    -0.07
    anuts
    -0.07
    viron
    -0.07
    amac
    -0.06
    misc
    -0.06
    POSITIVE LOGITS
     icon
    0.07
     ÑĩÑĤобÑĭ
    0.07
     links
    0.07
    loyd
    0.07
    ASN
    0.07
    ©
    0.06
     link
    0.06
    hy
    0.06
     Äijá»ĥ
    0.06
     button
    0.06
    Activations Density 0.017%

    No Known Activations