© 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. 20-LLAMASCOPE-RES-32K
    6. 11199
    Prev
    Next
    INDEX
    Explanations

    geographical references related to Brazil and other countries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lech
    -0.15
    wner
    -0.14
    clist
    -0.14
    icina
    -0.14
    ingly
    -0.14
    702
    -0.14
    illing
    -0.13
    گذ
    -0.13
    ách
    -0.13
    Ïĥμα
    -0.13
    POSITIVE LOGITS
    ischer
    0.22
    ian
    0.21
    ische
    0.21
    ÑģÑĤан
    0.20
    -American
    0.20
    -Russian
    0.20
    istan
    0.19
    ifornia
    0.18
    can
    0.18
     nationals
    0.18
    Activations Density 0.146%

    No Known Activations