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. 21106
    Prev
    Next
    INDEX
    Explanations

    statements or proposals related to environmental or health policies

    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
    eva
    -0.14
    دارÛĮ
    -0.14
    èµ·
    -0.14
    ÏĦή
    -0.14
    ptest
    -0.14
    Forbidden
    -0.13
    женÑĮ
    -0.13
    svc
    -0.13
    irim
    -0.13
    andest
    -0.13
    POSITIVE LOGITS
     unless
    0.31
     Unless
    0.26
    unless
    0.23
    Unless
    0.23
     society
    0.22
     there
    0.21
     we
    0.20
     if
    0.20
     solutions
    0.20
     without
    0.20
    Activations Density 0.353%

    No Known Activations