Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43807
    Prev
    Next
    INDEX
    Explanations

    occurrences of the first-person singular pronoun and its variants

    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
    erson
    -0.06
    aidu
    -0.05
    .Xaml
    -0.05
     kür
    -0.05
    roid
    -0.05
    ูà¹ī
    -0.05
    ctrine
    -0.05
     PureComponent
    -0.05
    lech
    -0.05
     Either
    -0.05
    POSITIVE LOGITS
     go
    0.11
     sit
    0.11
    gos
    0.10
     GO
    0.10
     stand
    0.09
     Go
    0.09
     goes
    0.09
     sits
    0.09
    go
    0.09
    _go
    0.09
    Activations Density 0.011%

    No Known Activations