Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 2-LLAMASCOPE-RES-32K
    6. 21911
    Prev
    Next
    INDEX
    Explanations

    imperative forms of verbs indicating actions or requests

    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
    umo
    -0.17
    ertools
    -0.16
    found
    -0.15
     micron
    -0.15
     found
    -0.15
     book
    -0.15
     deb
    -0.14
    itud
    -0.14
    out
    -0.14
    iversit
    -0.14
    POSITIVE LOGITS
    ursal
    0.15
    áv
    0.14
    -urlencoded
    0.14
    arching
    0.14
    hof
    0.13
    bane
    0.13
    ìŀ¡
    0.13
     znam
    0.13
    aepernick
    0.13
    оÑĩно
    0.13
    Activations Density 0.235%

    No Known Activations