© 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. 2272
    Prev
    Next
    INDEX
    Explanations

    sets of related items or concepts

    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
    edn
    -0.21
    ceased
    -0.15
    hal
    -0.14
    umd
    -0.14
    uer
    -0.14
    æľ
    -0.14
    nier
    -0.13
    enthal
    -0.13
    csi
    -0.13
    eri
    -0.13
    POSITIVE LOGITS
    tle
    0.25
    tlement
    0.22
    uptools
    0.22
    osa
    0.21
     forth
    0.20
    ups
    0.20
    sockopt
    0.19
    ings
    0.19
     aside
    0.19
    -up
    0.18
    Activations Density 0.033%

    No Known Activations