INDEX

Explanations

references to the word "there" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ermo

-0.18

uale

-0.18

-0.16

Ø®ØªÙĩ

-0.15

rix

-0.15

endas

-0.15

swap

-0.14

ip

-0.14

ocaly

-0.14

icode

-0.14

POSITIVE LOGITS

amburger

0.17

acks

0.16

ÑĩÐ°Ñģ

0.16

acas

0.15

 lives

0.14

fit

0.14

Ø³Ø§ÙĨÛĮ

0.14

Ner

0.13

bios

0.13

nergy

0.13

Activations Density 0.122%

references to the word "there" and its variations

No Comments

No Known Activations