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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95745
    Prev
    Next
    INDEX
    Explanations

    phrases related to therapy and self-improvement strategies

    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
    empor
    -0.06
    ucci
    -0.06
    agens
    -0.06
    IMP
    -0.06
    инÑĥв
    -0.06
    .connected
    -0.05
     vbCrLf
    -0.05
    uling
    -0.05
     cue
    -0.05
    omite
    -0.05
    POSITIVE LOGITS
    aylight
    0.08
    anzi
    0.07
    KD
    0.06
    анÑĥ
    0.06
    quir
    0.06
    iminal
    0.06
    ullo
    0.06
    ÑĨеÑģ
    0.06
    Stock
    0.06
    pn
    0.06
    Activations Density 0.131%

    No Known Activations