INDEX

Explanations

instances of polite requests or inquiries in conversation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

gaard

-0.17

å±ħæ°ĳ

-0.16

avar

-0.15

oque

-0.15

lu

-0.14

afa

-0.14

ynes

-0.14

ubs

-0.14

Ã¶m

-0.14

 bureaucr

-0.14

POSITIVE LOGITS

çĶ³

0.16

YRO

0.16

rana

0.16

erea

0.15

ROTO

0.14

rang

0.14

aptcha

0.14

Ð²Ð¸ÑĩÐ°Ð¹

0.13

agers

0.13

AGER

0.13

Activations Density 0.056%

instances of polite requests or inquiries in conversation

No Comments

No Known Activations