© 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. 8-LLAMASCOPE-RES-32K
    11. 6255
    Prev
    Next
    INDEX
    Explanations

    references to online casino games and gambling terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Donne
    -0.16
    FML
    -0.15
    .tp
    -0.14
    overy
    -0.13
    ondere
    -0.13
    aç
    -0.13
    ylko
    -0.13
    onn
    -0.13
    defer
    -0.13
    acho
    -0.13
    POSITIVE LOGITS
    alten
    0.16
    ponents
    0.15
     Arrest
    0.14
    )prepare
    0.14
    ½
    0.13
    dej
    0.13
     purity
    0.13
    tü
    0.13
    ηÏĤ
    0.13
    çĿ
    0.13
    Activations Density 0.010%

    No Known Activations