© 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 EvalsExportsAPI 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. 61037
    Prev
    Next
    INDEX
    Explanations

    punctuation marks used in dialogue

    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
    ίκ
    -0.08
    aint
    -0.08
     Ñģом
    -0.07
    æ§
    -0.07
    izard
    -0.07
    ikh
    -0.07
    uni
    -0.07
    echn
    -0.07
    ONTAL
    -0.07
    holm
    -0.07
    POSITIVE LOGITS
     Tie
    0.06
     incl
    0.06
     Craig
    0.06
    ret
    0.05
    elda
    0.05
    çĶ
    0.05
     Duel
    0.05
    irse
    0.05
     Sky
    0.05
    rens
    0.05
    Activations Density 0.000%

    No Known Activations