© 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. 26-LLAMASCOPE-RES-32K
    11. 28150
    Prev
    Next
    INDEX
    Explanations

    mentions of risks and challenges associated with various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulpt
    -0.19
    upp
    -0.15
    	extern
    -0.15
    abile
    -0.15
    essler
    -0.15
    anik
    -0.15
    kea
    -0.15
     indir
    -0.15
    eron
    -0.15
    iod
    -0.14
    POSITIVE LOGITS
     associated
    0.57
     involved
    0.57
    associated
    0.49
     Associated
    0.45
    Associated
    0.41
     assoc
    0.40
     associate
    0.39
     asoci
    0.38
     attached
    0.33
     associ
    0.32
    Activations Density 0.206%

    No Known Activations