© 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. 25-LLAMASCOPE-RES-32K
    6. 19332
    Prev
    Next
    INDEX
    Explanations

    variations of the word "program"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edList
    -0.18
    usher
    -0.17
     Masks
    -0.17
    Wunused
    -0.17
     Muj
    -0.16
    ough
    -0.16
    enburg
    -0.16
    altar
    -0.15
    stile
    -0.15
    pun
    -0.15
    POSITIVE LOGITS
    ming
    0.64
    med
    0.63
    mer
    0.56
    mers
    0.50
    mm
    0.48
    mes
    0.45
    ma
    0.45
    me
    0.44
    ms
    0.44
    MING
    0.41
    Activations Density 0.075%

    No Known Activations