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. 29-LLAMASCOPE-RES-32K
    6. 17667
    Prev
    Next
    INDEX
    Explanations

    terms related to power dynamics and sociopolitical structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovice
    -0.15
    ijke
    -0.15
    ylon
    -0.15
    onder
    -0.15
    stead
    -0.14
    onde
    -0.14
    iphers
    -0.14
    elidir
    -0.14
    IEL
    -0.14
    atrice
    -0.14
    POSITIVE LOGITS
    ism
    0.82
    ISM
    0.60
    isms
    0.57
    isme
    0.53
    ismo
    0.53
    ismus
    0.49
    izm
    0.49
    ismu
    0.45
    isma
    0.45
    主ä¹ī
    0.44
    Activations Density 0.076%

    No Known Activations