© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 12-LLAMASCOPE-RES-32K
    6. 32442
    Prev
    Next
    INDEX
    Explanations

    instances of the word "this."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oret
    -0.21
    orrent
    -0.18
     mes
    -0.15
     ab
    -0.14
     ger
    -0.14
    oga
    -0.14
     dom
    -0.14
    cum
    -0.14
     Titans
    -0.13
    èle
    -0.13
    POSITIVE LOGITS
    anas
    0.18
    dorf
    0.17
    лÑİ
    0.14
    akra
    0.14
    ARCH
    0.14
    aña
    0.14
    359
    0.14
    bÃŃ
    0.13
    _security
    0.13
    erval
    0.13
    Activations Density 0.084%

    No Known Activations