© 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. 14-LLAMASCOPE-RES-32K
    6. 13087
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence of external influences or factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iring
    -0.18
    @nate
    -0.16
    olini
    -0.15
    atever
    -0.14
    oretical
    -0.14
    ê¶ģ
    -0.14
     Pek
    -0.14
    اÙĨÛĮ
    -0.14
    createCommand
    -0.14
     Qual
    -0.14
    POSITIVE LOGITS
     matters
    0.24
     behalf
    0.23
     how
    0.22
     Matters
    0.19
     topics
    0.17
    how
    0.17
    ollapse
    0.17
     cómo
    0.16
    isse
    0.16
    avanaugh
    0.16
    Activations Density 0.139%

    No Known Activations