© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 18-LLAMASCOPE-RES-32K
    11. 28479
    Prev
    Next
    INDEX
    Explanations

    references to medical cancer terminology and advancements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĤ¹
    -0.16
    utra
    -0.15
     Ort
    -0.14
    çļĦå¿ĥ
    -0.14
    prus
    -0.14
    pras
    -0.14
    İ
    -0.14
    _rhs
    -0.13
    ypress
    -0.13
    Fore
    -0.13
    POSITIVE LOGITS
     Cancer
    0.46
     cancer
    0.43
     cancers
    0.34
     tumor
    0.32
     tum
    0.30
     tumors
    0.28
     chemotherapy
    0.26
     Onc
    0.26
     carcin
    0.25
    ancer
    0.24
    Activations Density 0.177%

    No Known Activations