INDEX

Explanations

phrases related to cooking times and methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

andom

-0.17

Ð¾ÑĢÐ°Ð·

-0.16

zen

-0.15

å®Ĺ

-0.14

 Talent

-0.14

 Literal

-0.14

Rai

-0.14

mbH

-0.13

.struct

-0.13

owan

-0.13

POSITIVE LOGITS

apia

0.14

 Kend

0.14

esk

0.13

 unreachable

0.13

ecome

0.13

-ves

0.13

å²Ĺ

0.13

EMU

0.13

plings

0.13

Activations Density 0.022%

phrases related to cooking times and methods

No Comments

No Known Activations