INDEX

Explanations

phrases indicating obstacles or impediments to action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

SError

-0.17

è§

-0.16

ilo

-0.15

åĬŁ

-0.14

alleries

-0.14

 GOODMAN

-0.14

acements

-0.14

/renderer

-0.14

awa

-0.14

 <!--[

-0.14

POSITIVE LOGITS

KB

0.16

zig

0.16

 unless

0.15

harma

0.15

à¹Ģà¸¥à¸¢

0.14

 Fahr

0.13

 simplex

0.13

 ster

0.13

 recovery

0.13

shr

0.13

Activations Density 0.261%

phrases indicating obstacles or impediments to action

No Comments

No Known Activations