© 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. 22-LLAMASCOPE-RES-131K
    11. 4107
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to identification and classification aspects of facilities or processes

    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
    eneg
    -0.07
    å¯Ħ
    -0.07
    uncios
    -0.07
    berapa
    -0.07
    umbn
    -0.06
    -regexp
    -0.06
    .promise
    -0.06
    åĬŀçIJĨ
    -0.06
    iliz
    -0.06
    ellij
    -0.06
    POSITIVE LOGITS
    udic
    0.07
     lev
    0.06
    icode
    0.06
     like
    0.06
     Soup
    0.06
    Ĩ
    0.06
    along
    0.06
    ews
    0.06
    inton
    0.06
     canc
    0.06
    Activations Density 0.015%

    No Known Activations