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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 29-LLAMASCOPE-RES-32K
    6. 17273
    Prev
    Next
    INDEX
    Explanations

    details related to scientific experimental procedures and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    á»ħ
    -0.15
     CONVERT
    -0.15
     ValueEventListener
    -0.14
     ActionTypes
    -0.14
    ickle
    -0.14
    ì»
    -0.14
    unma
    -0.14
    mojom
    -0.14
    deposit
    -0.14
     åĥ
    -0.14
    POSITIVE LOGITS
     buffer
    0.31
    buffer
    0.27
     Buffer
    0.26
     buffers
    0.25
    Buffer
    0.25
    -buffer
    0.24
     buffered
    0.24
     stock
    0.23
    _buffer
    0.23
     PBS
    0.22
    Activations Density 0.065%

    No Known Activations