© 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. 24-LLAMASCOPE-RES-32K
    6. 13775
    Prev
    Next
    INDEX
    Explanations

    the word "Apep" and its variations, indicating a focus on the mythological serpent associated with chaos in Egyptian mythology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    short
    -0.18
    sh
    -0.18
    mitt
    -0.18
    ship
    -0.17
    shop
    -0.16
    scar
    -0.16
    sek
    -0.16
    raj
    -0.16
    se
    -0.16
    esti
    -0.16
    POSITIVE LOGITS
    ptide
    0.26
    y
    0.23
    ptides
    0.22
    yer
    0.21
    achment
    0.19
    oples
    0.19
    yen
    0.17
    acock
    0.17
    aking
    0.17
    yat
    0.17
    Activations Density 0.020%

    No Known Activations