INDEX

Explanations

phrases and actions related to instructions or guidance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

agini

-0.15

eka

-0.14

pit

-0.14

aska

-0.14

ern

-0.13

ilinx

-0.13

å¼ĺ

-0.13

oulos

-0.13

udder

-0.13

 Bernstein

-0.13

POSITIVE LOGITS

0.15

 Sutton

0.15

zcze

0.15

ħn

0.14

hou

0.14

avad

0.14

<decltype

0.14

ØŃÙĬ

0.14

Zur

0.14

é¡ĶãĤĴ

0.14

Activations Density 1.561%

phrases and actions related to instructions or guidance

No Comments

No Known Activations