© 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. 4-LLAMASCOPE-RES-32K
    6. 24921
    Prev
    Next
    INDEX
    Explanations

    terms related to aspiration and ambition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stre
    -0.16
    hammer
    -0.15
    orean
    -0.14
    ighton
    -0.14
    els
    -0.14
    że
    -0.14
    ovi
    -0.14
    ei
    -0.14
    icaid
    -0.14
     Garner
    -0.13
    POSITIVE LOGITS
    ège
    0.15
    OTES
    0.15
    pus
    0.14
    omatic
    0.14
    739
    0.14
    riad
    0.14
    inalg
    0.14
    _mA
    0.14
    ếu
    0.14
    Ń
    0.14
    Activations Density 0.011%

    No Known Activations