INDEX

Explanations

occurrences of the word "span" 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 @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

yas

-0.17

ermann

-0.17

lus

-0.16

ystone

-0.16

-ÑĤÐ¾

-0.16

sb

-0.15

tt

-0.15

Spatial

-0.14

sk

-0.14

yne

-0.14

POSITIVE LOGITS

ned

0.30

ning

0.29

nable

0.27

iards

0.27

iard

0.26

 span

0.20

nung

0.20

 Span

0.19

ish

0.18

iel

0.18

Activations Density 0.012%

occurrences of the word "span" in various contexts

No Comments

No Known Activations