© 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. 28592
    Prev
    Next
    INDEX
    Explanations

    concepts related to connections and intersections 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 @ 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
    tog
    -0.15
     jumps
    -0.14
    TOTYPE
    -0.14
     alternating
    -0.14
    .opendaylight
    -0.14
    uche
    -0.14
    nth
    -0.14
    奴
    -0.14
    è·³
    -0.14
    TAIL
    -0.14
    POSITIVE LOGITS
     overlap
    0.36
     interaction
    0.36
     collision
    0.36
    collision
    0.34
     overlaps
    0.33
     interact
    0.33
     intersection
    0.32
     interacts
    0.32
     Collision
    0.32
     collisions
    0.31
    Activations Density 0.147%

    No Known Activations