INDEX

Explanations

time indicators related to events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ãģ¨ãĤĤ

-0.20

ut

-0.15

in

-0.15

vor

-0.15

ç·Ĵ

-0.15

ai

-0.14

ad

-0.13

UNUSED

-0.13

POSITIVE LOGITS

ET

0.18

reek

0.17

stantiate

0.17

lok

0.16

EST

0.16

stants

0.16

inges

0.16

CT

0.15

ãĥªãĥ³ãĤ°

0.15

ÑĨÐµÐ¿

0.15

Activations Density 0.016%

time indicators related to events

No Comments

No Known Activations