© 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. 62091
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate prior experience or tenure in a role

    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
    ieri
    -0.07
    ãģŁãģĹ
    -0.07
    Ãłng
    -0.06
    DEX
    -0.06
    aris
    -0.06
    cek
    -0.06
    hart
    -0.06
    áct
    -0.06
     گذ
    -0.06
    arus
    -0.06
    POSITIVE LOGITS
    atown
    0.07
    HITE
    0.07
    jeta
    0.06
    aben
    0.06
    uentes
    0.06
    bose
    0.06
     Äijó
    0.06
     those
    0.06
     Byrne
    0.06
    nicos
    0.06
    Activations Density 0.002%

    No Known Activations