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. 22689
    Prev
    Next
    INDEX
    Explanations

    specific phrases related to health and safety

    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
    onian
    -0.15
    oston
    -0.15
    vier
    -0.15
    xit
    -0.14
     бокÑĥ
    -0.14
    orp
    -0.14
    ailer
    -0.14
     COPYRIGHT
    -0.14
    cock
    -0.13
    ometown
    -0.13
    POSITIVE LOGITS
     ban
    0.17
    712
    0.15
    lü
    0.15
     ly
    0.14
     Coy
    0.14
    олÑı
    0.14
     Voll
    0.14
    veau
    0.14
     Freed
    0.14
    646
    0.14
    Activations Density 1.041%

    No Known Activations