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. 17-LLAMASCOPE-RES-32K
    6. 6104
    Prev
    Next
    INDEX
    Explanations

    instances of explosive or sudden actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izr
    -0.16
    nez
    -0.16
    ifax
    -0.15
    طر
    -0.15
    á»ĩ
    -0.15
    еÑĢÑĤ
    -0.15
    rai
    -0.15
    andum
    -0.14
    umin
    -0.14
    ibe
    -0.14
    POSITIVE LOGITS
     burst
    0.21
     Burst
    0.21
     bursts
    0.19
     into
    0.18
     bursting
    0.18
    çĤ¸
    0.18
    burst
    0.17
     forth
    0.17
    implode
    0.16
    743
    0.15
    Activations Density 0.048%

    No Known Activations