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. 25-LLAMASCOPE-RES-32K
    6. 16563
    Prev
    Next
    INDEX
    Explanations

    phrases that express subjective evaluations or perceptions of situations

    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
    ullo
    -0.18
    anke
    -0.15
     undisclosed
    -0.15
    uner
    -0.15
    amu
    -0.14
    iland
    -0.14
    anki
    -0.14
    blr
    -0.14
    iku
    -0.14
    ugi
    -0.14
    POSITIVE LOGITS
     innoc
    0.31
     straightforward
    0.28
     harmless
    0.27
     innocent
    0.24
     simple
    0.24
     obvious
    0.23
     normal
    0.22
     ordinary
    0.21
     Harm
    0.20
     initially
    0.20
    Activations Density 0.103%

    No Known Activations