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. 3-LLAMASCOPE-RES-32K
    6. 3684
    Prev
    Next
    INDEX
    Explanations

    the phrase "hold up" along with related forms and phrases indicating obstruction or resistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hot
    -0.15
     som
    -0.15
    UMB
    -0.15
     gro
    -0.15
     groove
    -0.14
     DbSet
    -0.14
    à¸ģระ
    -0.14
     norm
    -0.14
    uple
    -0.14
     stab
    -0.14
    POSITIVE LOGITS
    awl
    0.17
    prites
    0.15
     Zum
    0.14
    ftar
    0.14
    ÙĪØ¹
    0.14
    ìĿ´íĦ°
    0.14
    SCORE
    0.14
    enco
    0.14
    ibri
    0.14
    باÙĨ
    0.13
    Activations Density 0.006%

    No Known Activations