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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 89206
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods

    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
     trap
    -0.07
    pine
    -0.06
    isle
    -0.06
    ique
    -0.06
     Balt
    -0.06
    inet
    -0.06
     Reserve
    -0.06
     Trap
    -0.06
    iki
    -0.06
     reserve
    -0.06
    POSITIVE LOGITS
    ega
    0.07
    .scalablytyped
    0.07
    Means
    0.07
    eru
    0.07
    reau
    0.07
    hta
    0.07
    ootball
    0.07
    ãĤ¶ãĥ¼
    0.06
    OLDER
    0.06
    ORED
    0.06
    Activations Density 0.000%

    No Known Activations