© 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. 29496
    Prev
    Next
    INDEX
    Explanations

    specific suffixes and variations of names

    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
    zman
    -0.08
    lsen
    -0.07
    commons
    -0.07
    unma
    -0.07
    modele
    -0.06
    xmm
    -0.06
    με
    -0.06
    utin
    -0.06
    eming
    -0.06
    eward
    -0.06
    POSITIVE LOGITS
    illo
    0.08
    istrate
    0.07
    RIPT
    0.07
    ESSAGES
    0.06
    ìį¨
    0.06
    istrates
    0.06
     concrete
    0.06
    eller
    0.06
    ãĥĢãĥ¼
    0.06
    taÅŁ
    0.06
    Activations Density 0.067%

    No Known Activations