© 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. 128537
    Prev
    Next
    INDEX
    Explanations

    references to audio and communication systems technology

    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
    ãĥģãĥ¥
    -0.07
    045
    -0.07
    apur
    -0.07
    icles
    -0.07
    creds
    -0.06
    .mm
    -0.06
    aku
    -0.06
     COUR
    -0.06
    ebek
    -0.06
    /go
    -0.06
    POSITIVE LOGITS
    activex
    0.07
    :↵
    0.06
     anon
    0.06
    emez
    0.06
     patent
    0.06
    âijł
    0.06
     xOffset
    0.06
    munition
    0.06
     Patent
    0.05
     Anonymous
    0.05
    Activations Density 0.022%

    No Known Activations