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. 22-LLAMASCOPE-RES-32K
    6. 11232
    Prev
    Next
    INDEX
    Explanations

    terms related to legal advocacy and political organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enis
    -0.17
    ertz
    -0.15
    izia
    -0.14
    marshal
    -0.14
    usch
    -0.14
    icult
    -0.14
    InView
    -0.14
    AREST
    -0.14
    icense
    -0.14
    Ñĥма
    -0.14
    POSITIVE LOGITS
    ates
    0.45
    ate
    0.42
    ated
    0.37
    ately
    0.35
    ATE
    0.34
    ATES
    0.34
    ating
    0.28
    ATED
    0.27
    iate
    0.27
    aten
    0.25
    Activations Density 0.051%

    No Known Activations