© 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. 18-LLAMASCOPE-RES-32K
    6. 23925
    Prev
    Next
    INDEX
    Explanations

    contact information and business entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amma
    -0.16
    òa
    -0.15
    (utf
    -0.15
    yahoo
    -0.14
    Unc
    -0.14
    Ñıб
    -0.14
     Relief
    -0.13
    elve
    -0.13
    subj
    -0.13
    usz
    -0.13
    POSITIVE LOGITS
    communications
    0.21
     PR
    0.20
     communications
    0.20
     telephone
    0.19
    PR
    0.18
     phone
    0.18
     Communications
    0.18
     tel
    0.17
     media
    0.17
    éĽ»è©±
    0.17
    Activations Density 0.031%

    No Known Activations