© 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. 27-LLAMASCOPE-RES-32K
    11. 2115
    Prev
    Next
    INDEX
    Explanations

    concepts related to moral dilemmas and the complexities of rights and actions

    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
    andon
    -0.15
    ycop
    -0.14
    aml
    -0.14
    ãĥ¬ãĥ³
    -0.14
    legate
    -0.14
    ihan
    -0.13
    -alist
    -0.13
    ABL
    -0.13
    izabeth
    -0.13
    Normalization
    -0.13
    POSITIVE LOGITS
     benefit
    0.49
     Benefit
    0.39
    benef
    0.36
     advance
    0.34
     benefits
    0.33
     benef
    0.32
     benefited
    0.32
    Benef
    0.32
     benefiting
    0.31
     BEN
    0.30
    Activations Density 0.479%

    No Known Activations