INDEX

Explanations

proper nouns and specific events or titles

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

acker

-0.17

setattr

-0.17

 Tape

-0.16

rz

-0.16

rodu

-0.15

ascimento

-0.15

ilip

-0.14

vou

-0.14

 societies

-0.14

_INTERVAL

-0.14

POSITIVE LOGITS

(SS

0.32

(SC

0.23

SS

0.23

(S

0.22

(SP

0.19

NSS

0.18

NSS

0.17

SCT

0.17

.SC

0.17

SS

0.16

Activations Density 0.152%

proper nouns and specific events or titles

No Comments

No Known Activations