© 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. 26-LLAMASCOPE-RES-32K
    6. 6832
    Prev
    Next
    INDEX
    Explanations

    phrases indicating communication or contact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ACKET
    -0.17
    ompiler
    -0.16
    Forum
    -0.15
    typing
    -0.14
    ritz
    -0.14
    rud
    -0.14
     Dip
    -0.14
    iná
    -0.14
     ful
    -0.13
    illance
    -0.13
    POSITIVE LOGITS
     contact
    0.44
    contact
    0.36
     Contact
    0.33
     contacto
    0.32
    Contact
    0.31
     CONTACT
    0.31
     contacting
    0.31
     touch
    0.30
     Kontakt
    0.30
     contacted
    0.29
    Activations Density 0.032%

    No Known Activations