INDEX

Explanations

pairs of brackets or parentheses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 Morm

-0.17

yor

-0.15

Ø§

-0.15

pau

-0.14

 wealthiest

-0.14

åĽ³

-0.14

UNET

-0.14

crete

-0.14

bourne

-0.13

UBY

-0.13

POSITIVE LOGITS

Bar

0.15

MB

0.15

 imposing

0.14

SITE

0.14

-anchor

0.14

ulty

0.14

ä»ĺãģĳ

0.13

 Leather

0.13

mmo

0.13

 Gordon

0.13

Activations Density 0.009%

pairs of brackets or parentheses

No Comments

No Known Activations