© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106391
    Prev
    Next
    INDEX
    Explanations

    occurrences of the end punctuation in the text

    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
    лÑıн
    -0.06
    imeo
    -0.06
    ardo
    -0.06
    ady
    -0.06
    ilt
    -0.06
    abar
    -0.05
     E
    -0.05
    olas
    -0.05
     {{{
    -0.05
    èŁ
    -0.05
    POSITIVE LOGITS
     Bernstein
    0.07
    reon
    0.07
    auga
    0.07
    andır
    0.07
    ucken
    0.07
     Annunci
    0.07
     pad
    0.07
    uced
    0.07
    ause
    0.06
    iles
    0.06
    Activations Density 0.000%

    No Known Activations