© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 119054
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
    ostel
    -0.09
    usercontent
    -0.08
    оÐ
    -0.07
    enor
    -0.07
    erus
    -0.07
    erez
    -0.07
    retched
    -0.06
    aurant
    -0.06
    ısıyla
    -0.06
    contacts
    -0.06
    POSITIVE LOGITS
    udent
    0.06
     اث
    0.06
    å¬
    0.05
    ily
    0.05
     w
    0.05
     Elliott
    0.05
    enne
    0.05
    weigh
    0.05
     mold
    0.05
    inde
    0.05
    Activations Density 0.000%

    No Known Activations