© 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. 129061
    Prev
    Next
    INDEX
    Explanations

    references to the name "Conn" and its variations

    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
    strup
    -0.07
    .UnitTesting
    -0.07
    .scalablytyped
    -0.07
    ecko
    -0.07
    staking
    -0.07
    rama
    -0.07
    APPER
    -0.07
    DBObject
    -0.07
    oord
    -0.07
    ساÙĨÛĮ
    -0.07
    POSITIVE LOGITS
    olly
    0.08
    ors
    0.07
    emann
    0.07
     subt
    0.07
    rat
    0.06
    clave
    0.06
    ep
    0.06
    esta
    0.06
    kit
    0.06
    nect
    0.06
    Activations Density 0.006%

    No Known Activations