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. 31-LLAMASCOPE-RES-32K
    6. 18233
    Prev
    Next
    INDEX
    Explanations

    specific identifiers or unique symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    δά
    -0.15
    óÅĤ
    -0.13
    eken
    -0.13
     POLITICO
    -0.13
    -toggler
    -0.13
     eSports
    -0.13
    åŃĿ
    -0.13
     Assets
    -0.13
     Avatar
    -0.13
     ìĪĺìĥģ
    -0.13
    POSITIVE LOGITS
     Chin
    0.23
     Mar
    0.20
     J
    0.18
     Texas
    0.17
     Donald
    0.17
    DIM
    0.17
    chin
    0.16
     west
    0.16
     chin
    0.16
     east
    0.15
    Activations Density 0.003%

    No Known Activations