© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 26-LLAMASCOPE-RES-32K
    11. 11789
    Prev
    Next
    INDEX
    Explanations

    elements related to storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     parks
    -0.16
    Digest
    -0.15
     Digest
    -0.14
    åħ¬åľĴ
    -0.14
    digest
    -0.14
     Cathedral
    -0.14
    PFN
    -0.14
     metropolitan
    -0.14
    .office
    -0.14
     senators
    -0.13
    POSITIVE LOGITS
     village
    0.85
     Village
    0.74
     villages
    0.72
    æĿij
    0.67
     villagers
    0.60
     settlement
    0.46
    illage
    0.45
     settlements
    0.45
     Ñģела
    0.44
     köy
    0.43
    Activations Density 0.271%

    No Known Activations