INDEX

Explanations

instances of phrases or punctuation indicating uncertainty or questioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 passive

-0.15

 bodily

-0.14

ilter

-0.14

ÑĥÐ»Ñİ

-0.14

æ·

-0.14

NDER

-0.13

ãĥ¼ãĥĭ

-0.13

bsolute

-0.13

licer

-0.13

POSITIVE LOGITS

kees

0.17

airy

0.16

cas

0.15

AVOR

0.14

 sons

0.14

acas

0.14

fi

0.14

éĻ¸

0.14

ware

0.14

 Upper

0.14

Activations Density 0.004%

instances of phrases or punctuation indicating uncertainty or questioning

No Comments

No Known Activations