INDEX

Explanations

instances of the pronoun "I" and phrases indicating personal experiences or opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

marvin

-0.16

éĶģ

-0.16

readcr

-0.16

åĲ¾

-0.15

 myself

-0.15

enschaft

-0.15

odial

-0.15

ãĥĪãĥ«

-0.15

@nate

-0.14

.scalablytyped

-0.14

POSITIVE LOGITS

Uses

0.16

 empty

0.16

 bought

0.15

 used

0.15

 find

0.15

 Uses

0.15

 Ð¸ÑģÐ¿Ð¾Ð»ÑĮÐ·

0.15

 uses

0.15

buy

0.14

Activations Density 0.058%

instances of the pronoun "I" and phrases indicating personal experiences or opinions

No Comments

No Known Activations