© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-32K
    11. 19315
    Prev
    Next
    INDEX
    Explanations

    references to the word "Covenant" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alog
    -0.17
    वर
    -0.15
    TOR
    -0.15
    QUENCY
    -0.14
    ollar
    -0.14
    ãģĦãĤĭ
    -0.14
    áºŃ
    -0.14
    lings
    -0.13
    BAR
    -0.13
    atomy
    -0.13
    POSITIVE LOGITS
    ry
    0.20
    raman
    0.19
    ty
    0.18
    ripe
    0.17
    éry
    0.17
    rian
    0.15
    eyi
    0.15
    urers
    0.15
    rey
    0.15
    ech
    0.15
    Activations Density 0.004%

    No Known Activations