© 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. 23-LLAMASCOPE-RES-32K
    11. 28502
    Prev
    Next
    INDEX
    Explanations

    mentions of political party affiliations and committee involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Consortium
    -0.20
    asz
    -0.17
     Lutheran
    -0.16
    dba
    -0.16
     consortium
    -0.15
    .gov
    -0.15
    èĩ£
    -0.15
     Governor
    -0.15
    anki
    -0.14
    ampion
    -0.14
    POSITIVE LOGITS
     party
    0.41
     Party
    0.36
     PARTY
    0.33
    party
    0.32
    Party
    0.31
    _party
    0.27
     membership
    0.27
     leadership
    0.26
    åħļ
    0.26
    黨
    0.23
    Activations Density 0.095%

    No Known Activations