INDEX

Explanations

variations of the word "appear" and related forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

tober

-0.18

quet

-0.17

lobber

-0.16

bery

-0.15

top

-0.15

irie

-0.15

combe

-0.15

spir

-0.15

osit

-0.14

elop

-0.14

POSITIVE LOGITS

ances

0.24

antly

0.22

ance

0.16

LEM

0.16

0.15

ibling

0.15

encing

0.15

ative

0.15

0.14

aÅ¾

0.14

Activations Density 0.031%

variations of the word "appear" and related forms

No Comments

No Known Activations