© 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. 26077
    Prev
    Next
    INDEX
    Explanations

    actions and interactions between characters in the narrative

    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
    raj
    -0.15
    ling
    -0.15
    itag
    -0.14
     ifdef
    -0.14
    ynom
    -0.14
     sentiment
    -0.13
    ynet
    -0.13
    ynch
    -0.13
    aina
    -0.13
    Callable
    -0.13
    POSITIVE LOGITS
    hetto
    0.17
    echa
    0.16
    egrator
    0.15
    avaÅŁ
    0.15
    .rs
    0.15
    ieri
    0.15
    ugins
    0.14
    kili
    0.14
    lsi
    0.14
    obby
    0.14
    Activations Density 0.700%

    No Known Activations