INDEX

Explanations

instances of the word "cover" 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

ering

-0.16

swagen

-0.16

zing

-0.16

covered

-0.15

ãĥ³ãĥĸ

-0.15

èľľ

-0.15

riba

-0.15

scale

-0.14

epad

-0.14

alo

-0.14

POSITIVE LOGITS

gence

0.23

dale

0.21

alls

0.21

 story

0.20

story

0.19

 Story

0.17

plate

0.17

utra

0.17

iges

0.16

 letter

0.16

Activations Density 0.011%

instances of the word "cover" in various contexts

No Comments

No Known Activations