© 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. 27137
    Prev
    Next
    INDEX
    Explanations

    sentences that classify or describe specific entities or categories

    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
    _FAST
    -0.06
    aset
    -0.06
    iat
    -0.06
    igne
    -0.06
    ibles
    -0.06
    nung
    -0.06
    dg
    -0.06
    asing
    -0.06
    atra
    -0.06
    asc
    -0.06
    POSITIVE LOGITS
    ä¸Ģ级
    0.07
    Ĥæķ°
    0.07
    _NC
    0.07
    kenin
    0.07
    .codes
    0.06
    /misc
    0.06
    ÑĦек
    0.06
     Thiên
    0.06
    ìĨĮ
    0.06
    cest
    0.06
    Activations Density 0.003%

    No Known Activations