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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-LLAMASCOPE-RES-131K
    6. 5185
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verb "has" in various contexts

    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
     Yourself
    -0.08
    asons
    -0.07
    imar
    -0.07
    GuidId
    -0.07
    εÏģÏĮ
    -0.07
    -runner
    -0.07
    ersen
    -0.06
    ilion
    -0.06
    üss
    -0.06
    utsch
    -0.06
    POSITIVE LOGITS
     us
    0.12
     everyone
    0.12
     me
    0.10
     everybody
    0.09
    ogn
    0.08
     them
    0.08
     him
    0.08
     tongues
    0.07
    quier
    0.07
     consequences
    0.07
    Activations Density 0.035%

    No Known Activations