© 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. 125296
    Prev
    Next
    INDEX
    Explanations

    references to female subjects and their actions or experiences

    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
    less
    -0.08
    ounder
    -0.07
    ashi
    -0.07
    quate
    -0.07
    iction
    -0.06
    leine
    -0.06
    amp
    -0.06
    arger
    -0.06
    orical
    -0.06
    ridge
    -0.06
    POSITIVE LOGITS
    /her
    0.15
    zelf
    0.15
    -même
    0.14
    /us
    0.13
    /she
    0.12
    iner
    0.11
     próp
    0.11
    self
    0.10
    /th
    0.09
    SELF
    0.09
    Activations Density 0.010%

    No Known Activations