© 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. 30-LLAMASCOPE-RES-32K
    11. 24484
    Prev
    Next
    INDEX
    Explanations

    references to sexual assault and its related allegations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ASK
    -0.15
    ÐĴÐŀ
    -0.15
     args
    -0.15
    appl
    -0.15
    annonce
    -0.15
     Arguments
    -0.14
     reassure
    -0.13
    YK
    -0.13
     hoÅŁ
    -0.13
     measure
    -0.13
    POSITIVE LOGITS
     testified
    0.26
     testimony
    0.26
     testify
    0.24
     accounts
    0.23
     implic
    0.23
     details
    0.22
     recount
    0.22
     statements
    0.22
     test
    0.22
     alleged
    0.22
    Activations Density 0.178%

    No Known Activations