INDEX

Explanations

phrases indicating clarification or explanation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

·

-0.15

áº©n

-0.15

 tá»Ń

-0.14

uzey

-0.14

stdarg

-0.14

liste

-0.14

 Shift

-0.14

ÐĴÑĤ

-0.14

reon

-0.13

 Evet

-0.13

POSITIVE LOGITS

0.15

 Schwe

0.15

ewe

0.14

 Andersen

0.14

 technical

0.14

ddy

0.14

tru

0.14

rophe

0.13

MVC

0.13

 Carroll

0.13

Activations Density 0.072%

phrases indicating clarification or explanation

No Comments

No Known Activations