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. 2-LLAMASCOPE-RES-32K
    6. 25778
    Prev
    Next
    INDEX
    Explanations

    instances of the word "humble" and its variations, emphasizing themes of humility or modesty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umbs
    -0.15
    getto
    -0.15
    villa
    -0.15
    GED
    -0.15
    agrid
    -0.15
    icari
    -0.14
     hữu
    -0.14
    ged
    -0.14
    éĥ¡
    -0.14
    otor
    -0.14
    POSITIVE LOGITS
    .optional
    0.17
     componentDid
    0.16
     Nack
    0.16
     Vance
    0.15
     Ret
    0.15
     ret
    0.15
    isset
    0.15
     Hum
    0.14
    लब
    0.14
     Hed
    0.14
    Activations Density 0.009%

    No Known Activations