© 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. 24-LLAMASCOPE-RES-32K
    11. 5624
    Prev
    Next
    INDEX
    Explanations

    phrases related to slim business cards and their various attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rez
    -0.16
    çĶ
    -0.15
    à¸ļà¸Ĺ
    -0.15
    IDDEN
    -0.15
    umbs
    -0.15
    ÄĻż
    -0.14
    ismic
    -0.14
    åŀ
    -0.14
    reon
    -0.14
    _hook
    -0.14
    POSITIVE LOGITS
     cards
    0.48
     card
    0.44
     Cards
    0.42
    Cards
    0.37
    cards
    0.37
    card
    0.34
     Card
    0.33
    -card
    0.32
    _cards
    0.32
    ãĤ«ãĥ¼ãĥī
    0.31
    Activations Density 0.055%

    No Known Activations