© 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. 72949
    Prev
    Next
    INDEX
    Explanations

    timestamps and social media references

    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
     e
    -0.07
    atre
    -0.06
    .bam
    -0.06
     s
    -0.06
    ultz
    -0.06
    .opens
    -0.06
    crest
    -0.06
    inh
    -0.05
    jamin
    -0.05
     of
    -0.05
    POSITIVE LOGITS
    ORIES
    0.10
    -thumbnails
    0.09
    VIC
    0.08
    orian
    0.08
    getti
    0.07
    kim
    0.07
    iyim
    0.07
    ánt
    0.07
    grily
    0.07
    ÙĬÙĦاد
    0.07
    Activations Density 0.000%

    No Known Activations