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. 28-LLAMASCOPE-RES-32K
    6. 29966
    Prev
    Next
    INDEX
    Explanations

    expressions indicating a sense of geographical or contextual placement

    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
    æĮĻ
    -0.19
    -ie
    -0.14
    516
    -0.14
    -sidebar
    -0.14
    ispiel
    -0.13
    dcc
    -0.13
    grese
    -0.13
     voksne
    -0.13
    idelberg
    -0.13
     Ñĩин
    -0.12
    POSITIVE LOGITS
     relation
    0.76
     regard
    0.75
     respect
    0.74
     regards
    0.69
     terms
    0.64
     Relation
    0.61
    relation
    0.57
     respects
    0.56
    respect
    0.51
     respecto
    0.51
    Activations Density 0.352%

    No Known Activations