© 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. 23-LLAMASCOPE-RES-32K
    11. 20810
    Prev
    Next
    INDEX
    Explanations

    references to weather conditions and temperatures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cool
    -0.33
     Cool
    -0.32
    Cool
    -0.30
     cooling
    -0.30
    cool
    -0.28
     Cooler
    -0.28
     Cooling
    -0.28
     cooler
    -0.26
     cooled
    -0.26
     coolest
    -0.20
    POSITIVE LOGITS
     below
    0.28
     BELOW
    0.26
     minus
    0.23
    below
    0.23
     Below
    0.21
    _below
    0.19
    Below
    0.19
     sub
    0.19
     abaixo
    0.19
     bitter
    0.19
    Activations Density 0.044%

    No Known Activations