© 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. 4309
    Prev
    Next
    INDEX
    Explanations

    emphatic or significant statements through punctuation, primarily focusing on periods and semicolons

    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
    ainen
    -0.07
    ât
    -0.07
    ây
    -0.07
    .builders
    -0.07
    iye
    -0.07
    incerely
    -0.06
    AWN
    -0.06
     Zum
    -0.06
    ân
    -0.06
    esel
    -0.06
    POSITIVE LOGITS
    ĥn
    0.06
     "
    0.06
    aimassage
    0.06
    :UIAlert
    0.05
    807
    0.05
    ilere
    0.05
    anager
    0.05
    .IContainer
    0.05
     “
    0.05
    unifu
    0.05
    Activations Density 0.005%

    No Known Activations