Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 2-LLAMASCOPE-RES-32K
    6. 1963
    Prev
    Next
    INDEX
    Explanations

    comparative language, specifically the word "than" and its variations

    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
     Pron
    -0.16
    anders
    -0.16
    istant
    -0.16
    atan
    -0.15
    ħ
    -0.15
    edic
    -0.14
    ullen
    -0.14
    angl
    -0.14
    atsu
    -0.14
    verb
    -0.14
    POSITIVE LOGITS
    oire
    0.15
     Gent
    0.14
    .office
    0.14
    bilt
    0.14
     INLINE
    0.14
    IOR
    0.14
    readcr
    0.14
    .fn
    0.14
    ensburg
    0.13
    hani
    0.13
    Activations Density 0.027%

    No Known Activations