© 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. 15-LLAMASCOPE-RES-131K
    6. 90013
    Prev
    Next
    INDEX
    Explanations

    hyperlinks or reference links 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
     em
    -0.06
    abar
    -0.06
     ry
    -0.06
    éĢļãĤĬ
    -0.06
     restricted
    -0.05
     Fam
    -0.05
    lrt
    -0.05
     orbital
    -0.05
     terminal
    -0.05
     ride
    -0.05
    POSITIVE LOGITS
    izzo
    0.08
    alion
    0.08
    alty
    0.08
    лиÑħ
    0.07
    evin
    0.07
    .struts
    0.07
    ilot
    0.07
    ÑĬ
    0.07
    parer
    0.07
    ì¹´ëĿ¼
    0.07
    Activations Density 0.001%

    No Known Activations