© 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 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. 25-LLAMASCOPE-RES-32K
    11. 12531
    Prev
    Next
    INDEX
    Explanations

    expressions and concepts related to hospitality and invitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grave
    -0.15
    acons
    -0.15
    оÑħ
    -0.14
    Ñĥнок
    -0.14
     Grade
    -0.14
    endas
    -0.14
    AYS
    -0.14
     Gri
    -0.13
    ibold
    -0.13
     вив
    -0.13
    POSITIVE LOGITS
     guest
    0.71
     guests
    0.69
    guest
    0.64
    Guest
    0.63
     Guests
    0.60
     Guest
    0.60
    _guest
    0.54
     quests
    0.47
     гоÑģÑĤ
    0.46
    uest
    0.41
    Activations Density 0.140%

    No Known Activations