© 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. 3278
    Prev
    Next
    INDEX
    Explanations

    names and references to Eastern European theater works or characters

    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
    aktu
    -0.08
    è¶
    -0.08
    Ñģклад
    -0.08
    DataStream
    -0.08
    anford
    -0.08
    .builders
    -0.08
    ECT
    -0.07
    Äł
    -0.07
     zbo
    -0.07
    ácil
    -0.07
    POSITIVE LOGITS
     (
    0.06
    s
    0.06
    upal
    0.06
    rtl
    0.06
     “
    0.06
    (
    0.06
     ”
    0.06
    ity
    0.06
    éĥİ
    0.05
    /-
    0.05
    Activations Density 0.003%

    No Known Activations