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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 23-LLAMASCOPE-RES-32K
    11. 21957
    Prev
    Next
    INDEX
    Explanations

    terms related to passwords and security measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oleans
    -0.16
    pping
    -0.15
    fak
    -0.15
    lets
    -0.14
    ë§ī
    -0.14
    infeld
    -0.14
    upy
    -0.14
    OfYear
    -0.14
     Presidency
    -0.14
    adle
    -0.14
    POSITIVE LOGITS
    Strength
    0.22
     strength
    0.21
    _strength
    0.20
     Strength
    0.20
    phrase
    0.18
    /pass
    0.18
    -reset
    0.18
     protect
    0.17
     protected
    0.17
    strength
    0.17
    Activations Density 0.008%

    No Known Activations