© 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. 21-LLAMASCOPE-RES-32K
    11. 10102
    Prev
    Next
    INDEX
    Explanations

    references to additional items or elements within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acy
    -0.16
    afi
    -0.16
    afia
    -0.16
    oger
    -0.16
    elda
    -0.15
    irsch
    -0.15
    obi
    -0.14
    ube
    -0.14
    fn
    -0.14
    ZY
    -0.14
    POSITIVE LOGITS
     by
    0.35
     oleh
    0.26
     bợi
    0.23
     تÙĪسط
    0.20
    edBy
    0.20
    by
    0.18
     byt
    0.17
    _by
    0.16
    ByEmail
    0.15
    byn
    0.15
    Activations Density 0.040%

    No Known Activations