© 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. 24-LLAMASCOPE-RES-32K
    6. 20880
    Prev
    Next
    INDEX
    Explanations

    structured information such as release dates and roles related to specific films or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sometimes
    -0.14
    fasta
    -0.14
     unintention
    -0.14
    VALID
    -0.13
    ajor
    -0.13
    ItemAt
    -0.13
    /animate
    -0.13
    à¥Īल
    -0.13
    casts
    -0.13
    rzy
    -0.13
    POSITIVE LOGITS
     unknown
    0.73
    unknown
    0.65
     yet
    0.62
     Unknown
    0.60
    Unknown
    0.57
     unspecified
    0.57
     unidentified
    0.56
     TBD
    0.54
     UNKNOWN
    0.54
    yet
    0.53
    Activations Density 0.276%

    No Known Activations