© 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. 30-LLAMASCOPE-RES-32K
    11. 4346
    Prev
    Next
    INDEX
    Explanations

    phrases related to dining experiences and event invitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yaptıģı
    -0.17
    ̧
    -0.15
     addCriterion
    -0.14
    éĤ£æł·
    -0.14
     yani
    -0.13
    ำ
    -0.13
    ứa
    -0.13
    ovky
    -0.13
     jspb
    -0.13
    .ManyToMany
    -0.13
    POSITIVE LOGITS
     any
    0.57
     either
    0.47
     one
    0.41
     ANY
    0.39
    either
    0.37
    any
    0.36
     EITHER
    0.33
    ä»»ä½ķ
    0.32
     whichever
    0.32
     Either
    0.32
    Activations Density 0.400%

    No Known Activations