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. 16674
    Prev
    Next
    INDEX
    Explanations

    phrases relating to consumer expectations and the introduction of new products or ingredients

    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
    irma
    -0.14
    íĿ¬
    -0.14
    (targetEntity
    -0.14
    eteria
    -0.13
    adelphia
    -0.13
    sembled
    -0.12
    icont
    -0.12
    typings
    -0.12
    ucch
    -0.12
    ãĥĬãĥ«
    -0.12
    POSITIVE LOGITS
     come
    1.19
     comes
    1.15
     Come
    1.05
     came
    1.02
    come
    1.01
    Come
    1.00
     Comes
    0.98
     coming
    0.96
    comes
    0.96
    came
    0.87
    Activations Density 0.729%

    No Known Activations