© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4142
    Prev
    Next
    INDEX
    Explanations

    references to Samsung Galaxy smartphone models

    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
    erville
    -0.08
    quee
    -0.07
    ()."
    -0.06
    indr
    -0.06
    ÑĢаÑħ
    -0.06
    ļĮ
    -0.06
    abic
    -0.06
    onec
    -0.06
    illac
    -0.06
    á»ĵ
    -0.06
    POSITIVE LOGITS
     FName
    0.08
    ANTA
    0.07
    adol
    0.07
    viz
    0.07
     att
    0.06
     Forces
    0.06
    ordering
    0.06
    EEK
    0.06
    jang
    0.06
    ÙĬاÙĨ
    0.06
    Activations Density 0.004%

    No Known Activations