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. 21016
    Prev
    Next
    INDEX
    Explanations

    references to homeopathy and its practitioners

    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
    ropp
    -0.18
    ombok
    -0.17
    ãģ®ãģĬ
    -0.16
    Âį
    -0.15
    NEL
    -0.15
    cco
    -0.14
    ammers
    -0.14
    ouz
    -0.14
    eldo
    -0.14
    ield
    -0.14
    POSITIVE LOGITS
     men
    0.16
     intelligent
    0.16
     honest
    0.16
     infer
    0.16
     gentle
    0.16
     functionalities
    0.16
     sturdy
    0.15
    gent
    0.15
     Gent
    0.15
     distur
    0.15
    Activations Density 0.315%

    No Known Activations