© 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. 15-LLAMASCOPE-RES-131K
    11. 61942
    Prev
    Next
    INDEX
    Explanations

    phrases that refer to organizational structures or group affiliations

    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
    ipe
    -0.07
    ippo
    -0.07
    illary
    -0.07
    ucken
    -0.07
    zeich
    -0.07
    fat
    -0.06
    lád
    -0.06
    mae
    -0.06
    emetery
    -0.06
    hack
    -0.06
    POSITIVE LOGITS
    .rb
    0.07
    ÙĨدر
    0.07
    JI
    0.06
     iht
    0.06
    ê¸ī
    0.06
    ãĥ¼ãĥĦ
    0.06
    μι
    0.06
     naw
    0.06
    .DialogResult
    0.06
    dba
    0.06
    Activations Density 0.003%

    No Known Activations