© 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. 78799
    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
    andel
    -0.07
    atis
    -0.07
    ноÑģÑıÑĤ
    -0.06
    iefs
    -0.06
    877
    -0.06
    ignum
    -0.06
     pitches
    -0.06
    Apps
    -0.06
    ãĤįãģĨ
    -0.06
    ëħĦëıĦ
    -0.06
    POSITIVE LOGITS
    leting
    0.06
    .OS
    0.06
    egin
    0.06
    ORIZ
    0.06
    jest
    0.06
     Jorge
    0.06
    alach
    0.06
    awy
    0.06
     Forg
    0.06
     Floors
    0.06
    Activations Density 0.001%

    No Known Activations