© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 75428
    Prev
    Next
    INDEX
    Explanations

    discussions about personal struggles and relationships

    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
    .Solid
    -0.07
    ESSAGES
    -0.07
    _JUMP
    -0.06
    -addons
    -0.06
    ãģ¯ãģļ
    -0.06
    ãĥ§
    -0.06
    ICODE
    -0.06
    DataStream
    -0.06
    usan
    -0.06
     ÑģÑİ
    -0.06
    POSITIVE LOGITS
     mans
    0.06
     philanth
    0.06
    ád
    0.06
    elib
    0.06
    Now
    0.06
     unspecified
    0.06
     jet
    0.06
     intoler
    0.06
    olla
    0.06
     quot
    0.06
    Activations Density 0.009%

    No Known Activations