© 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. 23-LLAMASCOPE-RES-32K
    11. 21395
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "in" and variations of context surrounding it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ikat
    -0.15
     ëħĦëıĦë³Ħ
    -0.14
    ãģĵãĤį
    -0.14
     ÚĺاÙĨ
    -0.14
    gili
    -0.14
    aldi
    -0.14
    ulace
    -0.14
    infeld
    -0.14
    uite
    -0.13
    htable
    -0.13
    POSITIVE LOGITS
     theory
    0.19
    fty
    0.18
    ittal
    0.18
     practice
    0.18
    itt
    0.18
     stead
    0.17
    ital
    0.17
    å¹ķ
    0.16
     case
    0.16
     rare
    0.15
    Activations Density 0.171%

    No Known Activations