INDEX

Explanations

repeated or notable mentions of the letter 'S' or the word 'Stat.'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

è¦

-0.18

ODB

-0.17

ooke

-0.16

ostel

-0.15

alcon

-0.15

Ĥ¨

-0.15

CPP

-0.15

.ba

-0.15

aight

-0.14

whereIn

-0.14

POSITIVE LOGITS

esso

0.21

essa

0.18

mes

0.18

imate

0.18

lessly

0.18

0.17

oric

0.17

ess

0.16

«

0.16

imat

0.16

Activations Density 0.006%

repeated or notable mentions of the letter 'S' or the word 'Stat.'

No Comments

No Known Activations