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. 16-LLAMASCOPE-RES-32K
    6. 21092
    Prev
    Next
    INDEX
    Explanations

    phrases or conjunctions that connect ideas or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     strictly
    -0.14
    udit
    -0.13
     Strict
    -0.13
    pling
    -0.13
    cape
    -0.13
    ữ
    -0.13
    Strict
    -0.13
    aqu
    -0.13
    _attempts
    -0.12
     OR
    -0.12
    POSITIVE LOGITS
    raquo
    0.17
    /or
    0.17
    ROID
    0.16
    upil
    0.16
     Ach
    0.14
    specs
    0.14
    /of
    0.14
    arrant
    0.14
    argout
    0.14
     Wander
    0.14
    Activations Density 0.055%

    No Known Activations