© 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. 15-LLAMASCOPE-RES-131K
    6. 103704
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate actions or recommendations related to obtaining services or information

    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
    chy
    -0.09
    makt
    -0.08
     itself
    -0.07
    appy
    -0.07
    pcodes
    -0.07
    ekl
    -0.07
    ocr
    -0.07
    bject
    -0.07
    bsolute
    -0.07
     your
    -0.07
    POSITIVE LOGITS
     themselves
    0.21
     thems
    0.10
     their
    0.09
    Their
    0.08
    their
    0.07
     иÑħ
    0.07
     whom
    0.07
     ihren
    0.07
     Their
    0.07
     اÙĦذÙĬÙĨ
    0.07
    Activations Density 0.174%

    No Known Activations