INDEX

Explanations

instances of the letter 'H' 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 @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

uintptr

-0.15

ioso

-0.15

atican

-0.14

ifes

-0.14

Cyr

-0.14

monds

-0.14

 pole

-0.13

iffies

-0.13

umerator

-0.13

ipes

-0.13

POSITIVE LOGITS

ector

0.28

Ã©l

0.28

ugo

0.28

ans

0.27

ennie

0.27

elen

0.27

annah

0.26

jal

0.26

erman

0.25

annel

0.25

Activations Density 0.025%

instances of the letter 'H' in various contexts

No Comments

No Known Activations