© 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. 126235
    Prev
    Next
    INDEX
    Explanations

    expressions of community solidarity and support

    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
    ersion
    -0.07
    ONUS
    -0.07
    ùa
    -0.07
    kách
    -0.07
    é»
    -0.06
    orro
    -0.06
    ninger
    -0.06
    otine
    -0.06
    onus
    -0.06
    owitz
    -0.06
    POSITIVE LOGITS
     DNA
    0.06
    /problem
    0.06
     Rein
    0.05
    il
    0.05
    ืà¸Ļ
    0.05
    l
    0.05
     EITHER
    0.05
    /drivers
    0.05
     U
    0.05
     dna
    0.05
    Activations Density 0.001%

    No Known Activations