INDEX

Explanations

statements about products and their evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

erd

-0.16

vrier

-0.16

igos

-0.15

eba

-0.15

exampleModal

-0.15

abilitÃ©

-0.14

bble

-0.14

onn

-0.14

bil

-0.14

boru

-0.14

POSITIVE LOGITS

/stretch

0.17

à¸«à¸§

0.15

 limburg

0.15

CTSTR

0.15

 herein

0.14

PRESSION

0.14

 eskort

0.14

aÃ±a

0.14

tones

0.14

kees

0.14

Activations Density 0.066%

statements about products and their evaluations

No Comments

No Known Activations