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. 25-LLAMASCOPE-RES-32K
    6. 22974
    Prev
    Next
    INDEX
    Explanations

    references to cancer and its associated risks, particularly in relation to coffee consumption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è°·
    -0.16
     Chew
    -0.15
    olian
    -0.14
    isÃŃ
    -0.14
    ços
    -0.14
     Nursery
    -0.14
    aint
    -0.13
     Collapse
    -0.13
     amis
    -0.13
    /topics
    -0.13
    POSITIVE LOGITS
     cancer
    0.72
     Cancer
    0.64
     cancers
    0.57
    ancer
    0.46
     malign
    0.45
     tum
    0.43
     tumor
    0.41
     tumors
    0.40
     carcinoma
    0.39
     canc
    0.37
    Activations Density 0.152%

    No Known Activations