INDEX

Explanations

variations of the word "crow" or related to it in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

Ã¹ng

-0.15

ockets

-0.15

KO

-0.15

avern

-0.15

implify

-0.15

idge

-0.15

ãĥ¼ãĥł

-0.14

 Transport

-0.14

kor

-0.14

oug

-0.14

POSITIVE LOGITS

dfunding

0.27

ther

0.23

ning

0.20

leys

0.20

LEY

0.19

dera

0.19

thers

0.19

ded

0.19

ley

0.18

 wing

0.18

Activations Density 0.010%

variations of the word "crow" or related to it in various contexts

No Comments

No Known Activations