© 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. 16-LLAMASCOPE-RES-32K
    11. 8125
    Prev
    Next
    INDEX
    Explanations

    sentences that include the phrase "We" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    deb
    -0.16
    fol
    -0.16
    ctor
    -0.16
    wahl
    -0.16
    rias
    -0.15
    we
    -0.15
    mq
    -0.15
    åĢij
    -0.15
    uction
    -0.15
    ca
    -0.14
    POSITIVE LOGITS
    aver
    0.18
    akens
    0.17
    473
    0.16
    maz
    0.16
    esk
    0.15
    itere
    0.15
    bsite
    0.15
    eview
    0.15
    kich
    0.15
    ertz
    0.15
    Activations Density 0.138%

    No Known Activations