Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82822
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names related to individuals

    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
    agos
    -0.08
    _fwd
    -0.07
    ána
    -0.07
    áo
    -0.07
    .getElementsBy
    -0.07
    ниÑĤ
    -0.07
    .Debugger
    -0.07
    оваÑĢи
    -0.07
    INLINE
    -0.07
    eties
    -0.06
    POSITIVE LOGITS
    arya
    0.07
    ’s
    0.06
    's
    0.06
    :;↵
    0.06
    submenu
    0.05
    ìĦł
    0.05
     Subway
    0.05
    achel
    0.05
     hum
    0.05
     Evel
    0.05
    Activations Density 0.006%

    No Known Activations