© 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. 15-LLAMASCOPE-RES-32K
    6. 2485
    Prev
    Next
    INDEX
    Explanations

    references to web structure and coding standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kees
    -0.17
    otto
    -0.16
    htags
    -0.15
    het
    -0.14
    empo
    -0.14
    stra
    -0.14
    odo
    -0.14
    mut
    -0.14
    closure
    -0.14
    nown
    -0.14
    POSITIVE LOGITS
    ldr
    0.15
    iyan
    0.15
    dealloc
    0.15
    /MIT
    0.14
    iche
    0.14
     Rew
    0.14
    uda
    0.14
     triangle
    0.13
    IDL
    0.13
    Rew
    0.13
    Activations Density 0.009%

    No Known Activations