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. 25-LLAMASCOPE-RES-32K
    6. 10896
    Prev
    Next
    INDEX
    Explanations

    references to Google Cloud Dialogflow and related components

    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
    lg
    -0.15
    gro
    -0.15
     Leh
    -0.15
    293
    -0.14
    _rwlock
    -0.14
    zk
    -0.14
     Harm
    -0.14
     ÏĢεÏģί
    -0.14
    allen
    -0.14
    arching
    -0.14
    POSITIVE LOGITS
     Cloud
    0.26
     cloud
    0.23
    .googleapis
    0.23
     Pub
    0.23
    Cloud
    0.23
    .Cloud
    0.22
    .appspot
    0.21
     Big
    0.20
     bq
    0.20
     projectId
    0.20
    Activations Density 0.030%

    No Known Activations