© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 28750
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the significance or impact of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adies
    -0.14
    chant
    -0.14
    agine
    -0.14
    ukkan
    -0.14
    éĢŁ
    -0.13
    Ã¼ÄŁ
    -0.13
    огод
    -0.13
    ableView
    -0.13
    ively
    -0.13
    ors
    -0.13
    POSITIVE LOGITS
    oted
    0.32
    elow
    0.29
    gie
    0.27
    gest
    0.25
    -big
    0.23
    wig
    0.23
    amy
    0.23
    -ticket
    0.22
    /big
    0.22
    GEST
    0.22
    Activations Density 0.050%

    No Known Activations