INDEX

Explanations

words indicating the initiation or commencement of actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 overcome

-0.17

quote

-0.14

hy

-0.14

stone

-0.14

thr

-0.14

sexual

-0.14

uck

-0.13

loader

-0.13

stones

-0.13

OLLOW

-0.13

POSITIVE LOGITS

 happening

0.24

zia

0.18

 appearing

0.16

its

0.16

avit

0.15

appe

0.15

oad

0.15

áº¥m

0.15

 occurring

0.15

¶Į

0.14

Activations Density 0.051%

words indicating the initiation or commencement of actions or events

No Comments

No Known Activations