© 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. 27-LLAMASCOPE-RES-32K
    11. 11211
    Prev
    Next
    INDEX
    Explanations

    mentions of cheese and related food items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otr
    -0.17
    eus
    -0.17
    nings
    -0.16
    -minded
    -0.15
    ippet
    -0.15
     cheat
    -0.15
    ebin
    -0.15
    ept
    -0.15
    acet
    -0.15
    ships
    -0.15
    POSITIVE LOGITS
    burger
    0.33
    burg
    0.28
    ball
    0.22
    balls
    0.22
     fond
    0.20
    quake
    0.20
    board
    0.19
    ecake
    0.18
     fon
    0.18
     Fond
    0.17
    Activations Density 0.007%

    No Known Activations