INDEX

Explanations

the word "everything"

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

.scalablytyped

-0.18

rito

-0.17

chte

-0.15

ationally

-0.15

oran

-0.15

orque

-0.15

icut

-0.14

ANDOM

-0.14

cmc

-0.14

.FontStyle

-0.14

POSITIVE LOGITS

inv

0.15

libc

0.15

alia

0.15

Par

0.14

eses

0.14

ird

0.14

 kvin

0.14

 coordinates

0.14

0.13

Î¿Î½

0.13

Activations Density 0.014%

the word "everything"

No Comments

No Known Activations