© 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. 8-LLAMASCOPE-RES-32K
    11. 6758
    Prev
    Next
    INDEX
    Explanations

    definitions and classifications related to size, safety, and hazards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ency
    -0.18
    pector
    -0.16
    enstein
    -0.15
    ilden
    -0.15
    pect
    -0.14
     cond
    -0.14
    imen
    -0.14
    atform
    -0.14
     quadr
    -0.14
     pain
    -0.14
    POSITIVE LOGITS
    RITE
    0.17
     anybody
    0.15
     anything
    0.15
    -Clause
    0.15
     compressor
    0.14
    лада
    0.14
     definition
    0.14
    Definition
    0.14
    [--
    0.14
    çĮ
    0.14
    Activations Density 0.210%

    No Known Activations