© 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. 28538
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Virgin" or variations thereof in various contexts

    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
    gaard
    -0.17
    raman
    -0.17
    olars
    -0.17
    yps
    -0.17
    CAPE
    -0.16
    ÙĦاÙĦ
    -0.16
    aad
    -0.16
    recision
    -0.15
    drs
    -0.15
    ein
    -0.14
    POSITIVE LOGITS
    ie
    0.18
     Galactic
    0.18
     territory
    0.17
     Meg
    0.17
     Islands
    0.17
    vir
    0.17
    ity
    0.17
    038
    0.17
     Atlantic
    0.16
     Steele
    0.16
    Activations Density 0.003%

    No Known Activations