Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-32K
    6. 5427
    Prev
    Next
    INDEX
    Explanations

    references to relationships and feelings of affection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORK
    -0.14
    .hxx
    -0.14
    ständ
    -0.13
    vek
    -0.13
     cork
    -0.13
     cond
    -0.13
    herits
    -0.13
    ilar
    -0.13
    coe
    -0.13
    usp
    -0.13
    POSITIVE LOGITS
    ibase
    0.16
     зак
    0.14
    gba
    0.14
    RET
    0.14
    -sdk
    0.14
     derec
    0.14
    Americ
    0.14
    ocker
    0.14
    oa
    0.14
     Reporter
    0.14
    Activations Density 0.126%

    No Known Activations