© 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. 18-LLAMASCOPE-RES-32K
    11. 24792
    Prev
    Next
    INDEX
    Explanations

    concepts related to black holes and galaxy collisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hakk
    -0.17
     nat
    -0.16
    uve
    -0.16
    aho
    -0.15
     unfavor
    -0.15
    oven
    -0.14
     afl
    -0.14
    pard
    -0.14
    esters
    -0.14
     perm
    -0.14
    POSITIVE LOGITS
    ão
    0.18
    Feedback
    0.17
    -feedback
    0.16
     feedback
    0.16
     Feedback
    0.15
    ndern
    0.15
    _AG
    0.15
     Sloan
    0.15
     galaxy
    0.15
    ãĤīãģĹ
    0.15
    Activations Density 0.013%

    No Known Activations