© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 10-LLAMASCOPE-RES-32K
    11. 10941
    Prev
    Next
    INDEX
    Explanations

    phrases and terms surrounding community support and safety, particularly in contexts affecting vulnerable populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ILLS
    -0.18
    iddy
    -0.16
    å±ħ
    -0.15
     å¸Ĥ
    -0.14
    atars
    -0.14
    URES
    -0.13
    سÙĨ
    -0.13
    anga
    -0.13
     æ
    -0.13
    retty
    -0.13
    POSITIVE LOGITS
     soon
    0.22
     forthcoming
    0.19
    soon
    0.18
     be
    0.16
     upcoming
    0.16
    fol
    0.15
    ingly
    0.15
     future
    0.15
     Soon
    0.15
    ially
    0.15
    Activations Density 1.507%

    No Known Activations