© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 24-LLAMASCOPE-RES-32K
    11. 18800
    Prev
    Next
    INDEX
    Explanations

    instances of sensitive and proprietary information, particularly related to security and inventory issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thon
    -0.15
    thing
    -0.15
    ãĥªãĥ¼ãĤº
    -0.14
    sembl
    -0.14
    (es
    -0.14
    SharedPtr
    -0.14
     Thing
    -0.14
    elize
    -0.14
     thing
    -0.14
     approach
    -0.13
    POSITIVE LOGITS
     or
    0.15
     household
    0.14
    BufferData
    0.14
    quia
    0.14
     versus
    0.14
     Carpenter
    0.14
    irs
    0.13
     же
    0.13
    material
    0.13
    ftar
    0.13
    Activations Density 0.506%

    No Known Activations