© 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. 2-LLAMASCOPE-RES-32K
    11. 16480
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to falsehoods or misconceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤĪãģŃ
    -0.15
    izu
    -0.15
    .partition
    -0.14
    ware
    -0.14
     Tunnel
    -0.14
    atte
    -0.14
    enda
    -0.14
    umb
    -0.14
    -prepend
    -0.14
    atu
    -0.14
    POSITIVE LOGITS
     Solomon
    0.14
    ORTH
    0.14
    æĪ¸
    0.14
     Gerald
    0.14
    SError
    0.14
    afa
    0.14
    .spy
    0.14
    NAS
    0.13
    948
    0.13
    ys
    0.13
    Activations Density 0.047%

    No Known Activations