INDEX

Explanations

references to specific times and dates

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ebra

-0.16

æ·

-0.15

eva

-0.14

soc

-0.14

æģµ

-0.14

inea

-0.14

ALCHEMY

-0.14

 Lyme

-0.14

dehyde

-0.14

erchant

-0.14

POSITIVE LOGITS

ET

0.39

EST

0.39

PT

0.35

EST

0.35

 Eastern

0.33

ET

0.33

PT

0.32

 eastern

0.30

PST

0.30

pac

0.30

Activations Density 0.044%

references to specific times and dates

No Comments

No Known Activations