© 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. 29564
    Prev
    Next
    INDEX
    Explanations

    technical terms and metadata associated with data processing and documentation

    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
    pNet
    -0.07
    ulumi
    -0.07
    .RowStyle
    -0.07
    ucken
    -0.07
    omanip
    -0.07
    UGHT
    -0.06
     Vance
    -0.06
    _rng
    -0.06
    verse
    -0.06
    vince
    -0.06
    POSITIVE LOGITS
    =
    0.08
    =&
    0.07
    _=
    0.07
    *&
    0.06
    &type
    0.06
     lang
    0.06
    aton
    0.06
    .quick
    0.06
    illet
    0.06
    =get
    0.06
    Activations Density 0.015%

    No Known Activations