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. 8-LLAMASCOPE-RES-32K
    6. 7633
    Prev
    Next
    INDEX
    Explanations

    words associated with identity and cultural attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oli
    -0.16
    (æľĪ
    -0.14
    å»¶
    -0.14
    ENER
    -0.14
    irt
    -0.14
     Isle
    -0.14
    .scalablytyped
    -0.14
    ibel
    -0.14
    AGR
    -0.14
    ãĥ¯ãĤ¤ãĥĪ
    -0.14
    POSITIVE LOGITS
    .sharedInstance
    0.14
    prav
    0.14
    ekl
    0.14
    ówn
    0.14
    ophilia
    0.14
     Blow
    0.14
    wers
    0.13
    _UNIFORM
    0.13
    bsolute
    0.13
    kl
    0.13
    Activations Density 0.011%

    No Known Activations