Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 28-LLAMASCOPE-RES-32K
    6. 456
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "hesitation" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acias
    -0.19
    brook
    -0.18
    owitz
    -0.16
     INTERRUPTION
    -0.15
    jer
    -0.15
    bject
    -0.15
    ìķħ
    -0.15
    obile
    -0.15
    ables
    -0.14
    ninger
    -0.14
    POSITIVE LOGITS
     Branch
    0.15
    afil
    0.15
    han
    0.14
    墨
    0.14
     Pull
    0.14
    pe
    0.14
    ICS
    0.14
    321
    0.14
     skin
    0.14
    ÙĪÙĨ
    0.14
    Activations Density 0.046%

    No Known Activations