© 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. 11-LLAMASCOPE-RES-32K
    11. 627
    Prev
    Next
    INDEX
    Explanations

    recurring phrases or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    naissance
    -0.16
    دارÛĮ
    -0.15
    .heroku
    -0.15
    rieve
    -0.14
    m
    -0.14
    meni
    -0.14
     Portug
    -0.14
     fitte
    -0.14
    riter
    -0.13
    autiful
    -0.13
    POSITIVE LOGITS
    tic
    0.15
    pend
    0.14
     suic
    0.13
    446
    0.13
    é½IJ
    0.13
    annonce
    0.13
    783
    0.13
    per
    0.13
    _DT
    0.12
    tics
    0.12
    Activations Density 0.140%

    No Known Activations