© 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. 30-LLAMASCOPE-RES-32K
    11. 16889
    Prev
    Next
    INDEX
    Explanations

    events or situations involving bears

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Butterfly
    -0.17
    rido
    -0.17
    æī¶
    -0.16
     lizard
    -0.16
     Pony
    -0.15
     poultry
    -0.15
     Millet
    -0.15
    ogra
    -0.15
     frog
    -0.15
     serpent
    -0.14
    POSITIVE LOGITS
     bears
    0.52
     bear
    0.52
     Bears
    0.44
     Bear
    0.44
    bear
    0.39
    Bear
    0.39
    çĨĬ
    0.37
     cub
    0.33
     Urs
    0.30
     polar
    0.29
    Activations Density 0.020%

    No Known Activations