© 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. 87787
    Prev
    Next
    INDEX
    Explanations

    proper nouns, primarily names and titles within the text

    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
    ượ
    -0.09
    име
    -0.08
    _OCCURRED
    -0.08
    éĺħ读次æķ°
    -0.08
    à¸Ļาà¸Ķ
    -0.07
     naš
    -0.07
    اضر
    -0.07
    #__
    -0.07
    rapper
    -0.07
    ulumi
    -0.07
    POSITIVE LOGITS
     said
    0.07
     says
    0.07
     spokesman
    0.07
    olars
    0.06
     spokeswoman
    0.06
    nesty
    0.05
    Âłin
    0.05
    Âłs
    0.05
     mess
    0.05
    489
    0.05
    Activations Density 0.041%

    No Known Activations