© 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. 23-LLAMASCOPE-RES-32K
    11. 30838
    Prev
    Next
    INDEX
    Explanations

    mentions of hair, especially blonde hair and its different styles or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flesh
    -0.18
    erea
    -0.17
     flesh
    -0.14
    irt
    -0.14
    üf
    -0.14
    eczy
    -0.14
    ivot
    -0.14
    еÑĢин
    -0.13
     Dot
    -0.13
    htub
    -0.13
    POSITIVE LOGITS
     hair
    0.50
     Hair
    0.42
    Hair
    0.40
    hair
    0.38
     locks
    0.37
     blond
    0.36
     blonde
    0.35
    髪
    0.35
     волоÑģ
    0.34
     curls
    0.32
    Activations Density 0.107%

    No Known Activations