Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 24-LLAMASCOPE-RES-32K
    6. 21196
    Prev
    Next
    INDEX
    Explanations

    terms related to cable services and products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amel
    -0.17
    åłĤ
    -0.16
    ERV
    -0.15
    edir
    -0.15
    etten
    -0.14
    icast
    -0.14
    deaux
    -0.14
    edb
    -0.14
    .VK
    -0.14
    ernaut
    -0.14
    POSITIVE LOGITS
    vision
    0.27
     television
    0.20
     TV
    0.20
    -TV
    0.20
    levision
    0.18
    TV
    0.18
     tv
    0.18
    grams
    0.16
     Television
    0.16
     Tv
    0.16
    Activations Density 0.007%

    No Known Activations