© 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. 20-LLAMASCOPE-RES-32K
    11. 24176
    Prev
    Next
    INDEX
    Explanations

    content related to harmful or offensive behavior and violations of guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uble
    -0.18
    rego
    -0.16
    ocular
    -0.14
    лоп
    -0.14
    ution
    -0.14
    alie
    -0.14
    765
    -0.14
    ogle
    -0.14
    yssey
    -0.14
    ogany
    -0.14
    POSITIVE LOGITS
     offensive
    0.20
     Offensive
    0.16
     nudity
    0.15
     invasion
    0.15
    Ùħبر
    0.15
    esin
    0.15
    _again
    0.15
    addle
    0.15
     Content
    0.14
     Heath
    0.14
    Activations Density 0.050%

    No Known Activations