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. 10-LLAMASCOPE-RES-32K
    6. 23335
    Prev
    Next
    INDEX
    Explanations

    alphanumeric sequences and URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wk
    -0.15
    nad
    -0.14
    emm
    -0.14
    rijk
    -0.14
    NavItem
    -0.14
    oval
    -0.14
    &m
    -0.14
    å§«
    -0.14
    avig
    -0.14
    .epsilon
    -0.14
    POSITIVE LOGITS
    rada
    0.17
    owell
    0.14
    lis
    0.14
     Yap
    0.14
    beth
    0.14
    illage
    0.14
    .getError
    0.14
    entarios
    0.13
    MPI
    0.13
    attles
    0.13
    Activations Density 0.007%

    No Known Activations