© 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. 57563
    Prev
    Next
    INDEX
    Explanations

    references to technology, specifically Google's products and services

    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
     whilst
    -0.08
     amongst
    -0.07
    ialog
    -0.07
     anyways
    -0.07
    exus
    -0.07
    ctic
    -0.06
    .ly
    -0.06
     Whilst
    -0.06
     Fancy
    -0.06
    osu
    -0.06
    POSITIVE LOGITS
     staffers
    0.07
    .Cmd
    0.06
    à¥įरà¤Ń
    0.06
    cha
    0.06
     Web
    0.06
    _emit
    0.06
    cho
    0.06
    roupon
    0.06
    ategori
    0.06
    çĨŁ
    0.06
    Activations Density 0.004%

    No Known Activations