© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126844
    Prev
    Next
    INDEX
    Explanations

    HTML and XML tags and related symbols

    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
    ibraltar
    -0.07
    824
    -0.07
    ibi
    -0.07
    enko
    -0.06
     lines
    -0.06
    erd
    -0.06
    reated
    -0.06
     raw
    -0.06
     ensemble
    -0.06
    onom
    -0.06
    POSITIVE LOGITS
    _NE
    0.07
    ũi
    0.07
    ãĢĶ
    0.07
    PIC
    0.07
    çĵľ
    0.06
    .Persistent
    0.06
    Lik
    0.06
     beginnings
    0.06
     hyperlink
    0.06
    favor
    0.06
    Activations Density 0.001%

    No Known Activations