© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 6-LLAMASCOPE-RES-32K
    6. 28110
    Prev
    Next
    INDEX
    Explanations

    references to crime and criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aping
    -0.15
    eriod
    -0.15
    æĪ»
    -0.15
    tlement
    -0.14
    aped
    -0.14
    ยà¸ĩ
    -0.14
    inery
    -0.14
    siniz
    -0.14
    ding
    -0.14
    lying
    -0.14
    POSITIVE LOGITS
    fully
    0.17
    δα
    0.14
    ancial
    0.14
    balls
    0.14
    andle
    0.13
    ivec
    0.13
    FileInfo
    0.13
    ully
    0.13
    çķ
    0.13
    chl
    0.13
    Activations Density 0.017%

    No Known Activations