© 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. 28-LLAMASCOPE-RES-32K
    11. 22863
    Prev
    Next
    INDEX
    Explanations

    words associated with confinement or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Builder
    -0.15
    amura
    -0.15
    (Buffer
    -0.15
    deaux
    -0.14
    (Bundle
    -0.14
    /block
    -0.14
    mgr
    -0.14
    mund
    -0.14
    exact
    -0.13
    tries
    -0.13
    POSITIVE LOGITS
    bs
    0.67
    b
    0.67
    ba
    0.54
    bed
    0.54
    б
    0.50
    be
    0.49
    bd
    0.49
    bb
    0.49
    bc
    0.48
    bin
    0.48
    Activations Density 0.148%

    No Known Activations