© 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. 9-LLAMASCOPE-RES-131K
    11. 95636
    Prev
    Next
    INDEX
    Explanations

    geographic locations specifically related to capes and points

    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
    adele
    -0.08
    udas
    -0.07
    ajas
    -0.07
    otten
    -0.07
    ocale
    -0.07
     MainAxisAlignment
    -0.07
    ett
    -0.07
    ocked
    -0.07
    preter
    -0.07
    Ĵáŀ
    -0.07
    POSITIVE LOGITS
    y
    0.06
    nez
    0.06
    ij
    0.06
     weather
    0.06
    yen
    0.05
    ÑĢаз
    0.05
    ward
    0.05
    finite
    0.05
    à¥Ģद
    0.05
    iden
    0.05
    Activations Density 0.014%

    No Known Activations