INDEX

Explanations

occurrences of the letter "R" 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 @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

isk

-0.15

Ð¾Ð·Ñĸ

-0.15

agua

-0.15

outu

-0.15

ich

-0.14

bill

-0.14

/Dk

-0.14

zie

-0.14

aoke

-0.14

Nos

-0.14

POSITIVE LOGITS

&B

0.22

ilan

0.19

ascal

0.18

haps

0.17

ZA

0.16

ilo

0.16

 Bene

0.16

-rated

0.16

apture

0.15

attle

0.15

Activations Density 0.029%

occurrences of the letter "R" in various contexts

No Comments

No Known Activations