© 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. 27-LLAMASCOPE-RES-32K
    6. 2860
    Prev
    Next
    INDEX
    Explanations

    phrases indicating client relationships and service commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Martial
    -0.18
    mile
    -0.17
     martial
    -0.16
     MIL
    -0.16
     Mapper
    -0.15
     Manning
    -0.15
    MASK
    -0.15
    æ¯Ľ
    -0.15
    mapper
    -0.15
    mia
    -0.15
    POSITIVE LOGITS
    Mc
    1.21
     mc
    1.12
     Mc
    1.09
     MC
    1.06
    mc
    1.02
    MC
    0.98
    _mc
    0.98
    .mc
    0.96
    (mc
    0.91
     McG
    0.89
    Activations Density 0.045%

    No Known Activations