Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 4-LLAMASCOPE-RES-32K
    6. 30918
    Prev
    Next
    INDEX
    Explanations

    legal terms and conditions related to obligations and requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    APPER
    -0.15
    studio
    -0.14
    sik
    -0.14
    cene
    -0.13
    ữu
    -0.13
    fak
    -0.13
    urovision
    -0.13
    olley
    -0.13
    ÏĦικ
    -0.13
    :numel
    -0.13
    POSITIVE LOGITS
    ouns
    0.15
    holm
    0.15
    fy
    0.15
    atten
    0.15
     pros
    0.14
    ait
    0.14
    odal
    0.13
     Amit
    0.13
    ök
    0.13
    675
    0.13
    Activations Density 0.110%

    No Known Activations