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. 7-LLAMASCOPE-RES-32K
    6. 17582
    Prev
    Next
    INDEX
    Explanations

    terms related to vaccinations and immunization practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idel
    -0.16
     fidelity
    -0.16
    /sites
    -0.15
    aja
    -0.15
    arge
    -0.14
    URY
    -0.14
    ilm
    -0.14
    dl
    -0.14
    ury
    -0.14
    LOY
    -0.14
    POSITIVE LOGITS
    ibling
    0.17
    CompleteListener
    0.16
    SystemService
    0.15
    ilis
    0.15
    ept
    0.14
    itin
    0.14
    ãĥ³ãĥĹ
    0.14
    .newBuilder
    0.14
     ÎķÎł
    0.14
    SFML
    0.13
    Activations Density 0.018%

    No Known Activations