© 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. 20-LLAMASCOPE-RES-32K
    11. 21749
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "In X," where X can be a time reference or a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spite
    -0.20
    duct
    -0.19
    sofar
    -0.19
    uro
    -0.17
    ena
    -0.16
    ¢åįķ
    -0.16
    ugu
    -0.15
    ovo
    -0.15
    rose
    -0.15
    /by
    -0.15
    POSITIVE LOGITS
     fact
    0.18
     instance
    0.17
     essence
    0.17
    immel
    0.17
     cases
    0.17
     indeed
    0.17
     recent
    0.16
     sum
    0.16
     instances
    0.15
     Indeed
    0.15
    Activations Density 0.113%

    No Known Activations