© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 29-LLAMASCOPE-RES-32K
    11. 12127
    Prev
    Next
    INDEX
    Explanations

    terms related to health and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HEALTH
    -0.25
     Health
    -0.22
     healthier
    -0.21
     health
    -0.21
    Health
    -0.20
    _HEALTH
    -0.20
    health
    -0.20
    åģ¥åº·
    -0.19
     salud
    -0.18
    _health
    -0.18
    POSITIVE LOGITS
     welfare
    0.23
     well
    0.23
     wealth
    0.22
     Well
    0.22
     fitness
    0.21
     Wealth
    0.21
     wel
    0.21
     Welfare
    0.21
     beauty
    0.19
     wellbeing
    0.19
    Activations Density 0.030%

    No Known Activations