© 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. 29-LLAMASCOPE-RES-32K
    11. 12751
    Prev
    Next
    INDEX
    Explanations

    keywords associated with conservation efforts and animal protection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chick
    -0.18
     paddle
    -0.18
     Ducks
    -0.17
     moll
    -0.16
    emoc
    -0.16
    泡
    -0.16
    bubble
    -0.16
     turtles
    -0.15
     Eggs
    -0.15
    culo
    -0.15
    POSITIVE LOGITS
     tiger
    0.48
     Tiger
    0.47
     lion
    0.45
     Tigers
    0.45
     lions
    0.42
     Lion
    0.40
    lion
    0.38
     Lions
    0.37
     Panther
    0.35
     Tig
    0.33
    Activations Density 0.070%

    No Known Activations