© 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. 9-LLAMASCOPE-RES-32K
    11. 2538
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    YL
    -0.17
    onto
    -0.16
    antal
    -0.16
    irie
    -0.15
    olum
    -0.15
    ent
    -0.15
    ulu
    -0.14
     ff
    -0.14
    oir
    -0.14
    enson
    -0.14
    POSITIVE LOGITS
    htdocs
    0.16
    241
    0.15
    ÑĤий
    0.14
    972
    0.14
    /Peak
    0.14
    iyel
    0.14
    POCH
    0.14
    Means
    0.14
    -toggler
    0.14
    !=(
    0.14
    Activations Density 0.020%

    No Known Activations