© 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. 5-LLAMASCOPE-RES-32K
    11. 16296
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "halo" or "halos" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ALS
    -0.15
     Preview
    -0.15
    tlement
    -0.14
    iyi
    -0.14
    ture
    -0.14
     Sty
    -0.14
    äll
    -0.14
    ly
    -0.14
    als
    -0.13
    ray
    -0.13
    POSITIVE LOGITS
    IFORM
    0.16
    istine
    0.15
    onet
    0.14
     elev
    0.14
    ental
    0.14
     Å¡kola
    0.14
     dri
    0.14
    ved
    0.14
    .fromString
    0.14
    uced
    0.13
    Activations Density 0.004%

    No Known Activations