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. 10809
    Prev
    Next
    INDEX
    Explanations

    elements related to identification or classification

    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
     Ngh
    -0.16
    ernet
    -0.15
    COVID
    -0.15
    веÑĢж
    -0.15
     COVID
    -0.14
     Gür
    -0.13
     covid
    -0.13
     Gry
    -0.13
     Drugs
    -0.13
    shiv
    -0.13
    POSITIVE LOGITS
     WALL
    0.38
     robot
    0.30
     robots
    0.29
     Wall
    0.28
     Pixar
    0.28
     Robots
    0.26
     Robot
    0.25
    _WALL
    0.24
    robots
    0.24
     anim
    0.24
    Activations Density 0.003%

    No Known Activations