© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 26-LLAMASCOPE-RES-32K
    6. 10331
    Prev
    Next
    INDEX
    Explanations

    terms related to championship titles and victories in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jax
    -0.15
    sson
    -0.15
    atica
    -0.15
    swagen
    -0.15
    ewan
    -0.14
    483
    -0.14
    anou
    -0.14
    ãģĺ
    -0.14
    lector
    -0.14
    Overrides
    -0.14
    POSITIVE LOGITS
     champion
    0.51
     title
    0.50
     titles
    0.47
     champions
    0.45
     Champion
    0.43
     championship
    0.41
     championships
    0.40
     champ
    0.39
     Title
    0.38
     tit
    0.37
    Activations Density 0.148%

    No Known Activations