© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 30-LLAMASCOPE-RES-32K
    6. 21696
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to cryptography and its systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ewolf
    -0.15
    dorf
    -0.15
    rop
    -0.15
    lical
    -0.15
     повин
    -0.14
    lob
    -0.14
    omb
    -0.13
    gis
    -0.13
     clam
    -0.13
    list
    -0.13
    POSITIVE LOGITS
     Funk
    0.21
     Bere
    0.18
    Mess
    0.18
     Mess
    0.17
     Kenn
    0.17
     mole
    0.17
     Fest
    0.17
     Str
    0.17
     mess
    0.16
     Element
    0.16
    Activations Density 0.011%

    No Known Activations