© 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. 17-LLAMASCOPE-RES-32K
    11. 26953
    Prev
    Next
    INDEX
    Explanations

    terms related to hair loss and restoration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vc
    -0.15
    imon
    -0.15
    .hu
    -0.14
    arty
    -0.14
    uml
    -0.14
    DEL
    -0.14
    brate
    -0.14
    ãng
    -0.14
    igu
    -0.14
    -js
    -0.14
    POSITIVE LOGITS
     hair
    0.28
     bald
    0.28
     Hair
    0.26
    Hair
    0.23
     hairs
    0.21
     Bald
    0.21
     follic
    0.20
     saç
    0.20
    pecia
    0.20
     scalp
    0.20
    Activations Density 0.025%

    No Known Activations