INDEX

Explanations

descriptions of challenging tasks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

iforn

-0.14

ulings

-0.14

 conven

-0.14

hiba

-0.13

OSH

-0.13

teg

-0.13

rav

-0.13

oS

-0.13

à¥įà¤°à¤¦

-0.12

íķĻíļĮ

-0.12

POSITIVE LOGITS

 task

0.94

task

0.76

 tasks

0.73

ä»»åĬ¡

0.70

 Task

0.68

-task

0.66

 TASK

0.65

Task

0.65

_task

0.63

.task

0.60

Activations Density 0.229%

descriptions of challenging tasks

No Comments

No Known Activations