© 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. 25-LLAMASCOPE-RES-32K
    11. 10922
    Prev
    Next
    INDEX
    Explanations

    references to personal and contact information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idUser
    -0.18
    ennen
    -0.18
    LowerCase
    -0.15
    aida
    -0.14
    iat
    -0.14
    imiz
    -0.13
    ipop
    -0.13
    enen
    -0.13
    :CGRect
    -0.13
    iny
    -0.13
    POSITIVE LOGITS
     address
    0.35
     addresses
    0.31
     phone
    0.30
     contact
    0.28
     zip
    0.28
     telephone
    0.26
     name
    0.26
     mailing
    0.24
     Address
    0.24
     adress
    0.23
    Activations Density 0.211%

    No Known Activations