© 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. 2-LLAMASCOPE-RES-32K
    11. 375
    Prev
    Next
    INDEX
    Explanations

    repeated patterns involving the sequence "hara" and "hs"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ecom
    -0.15
    airs
    -0.15
    ffen
    -0.14
     forb
    -0.14
    >\<^
    -0.14
    ding
    -0.13
    286
    -0.13
    .getUsername
    -0.13
     segments
    -0.13
    uci
    -0.13
    POSITIVE LOGITS
    essian
    0.16
    piel
    0.15
    elda
    0.15
    redd
    0.15
    vl
    0.15
    ıi
    0.14
     Payne
    0.14
    stab
    0.14
    asin
    0.14
    uft
    0.14
    Activations Density 0.025%

    No Known Activations