INDEX

Explanations

instances of the word "been" 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 @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

alse

-0.14

ÑĢÐ°Ñģ

-0.14

culate

-0.14

 createState

-0.14

onium

-0.14

ifle

-0.14

.environment

-0.14

panse

-0.13

rac

-0.13

agnostic

-0.13

POSITIVE LOGITS

ãĥĥãĥī

0.15

urt

0.15

ARA

0.15

uci

0.14

hani

0.14

icycle

0.14

orth

0.14

Rut

0.14

fre

0.13

itt

0.13

Activations Density 0.050%

instances of the word "been" in various contexts

No Comments

No Known Activations