INDEX

Explanations

references to the word "Wood" 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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ÑİÑĤ

-0.15

amespace

-0.15

StringBuilder

-0.14

.rs

-0.14

ologia

-0.14

amide

-0.14

eload

-0.14

uv

-0.14

irs

-0.14

.synthetic

-0.14

POSITIVE LOGITS

bury

0.24

row

0.24

stock

0.23

bine

0.22

side

0.21

cock

0.21

ward

0.21

son

0.20

wards

0.20

lands

0.18

Activations Density 0.012%

references to the word "Wood" in various contexts

No Comments

No Known Activations