INDEX

Explanations

phrases indicating conditional relationships or requirements for actions to occur

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ninger

-0.14

 æ¹

-0.14

Extras

-0.14

etime

-0.14

_USAGE

-0.14

fal

-0.14

jal

-0.14

UiThread

-0.13

rowable

-0.13

POSITIVE LOGITS

redo

0.17

iband

0.15

fers

0.15

ÙģÙĨ

0.15

ument

0.14

Ã¤lt

0.14

_indx

0.14

ë³´ê³ł

0.14

llu

0.14

vit

0.13

Activations Density 0.467%

phrases indicating conditional relationships or requirements for actions to occur

No Comments

No Known Activations