INDEX

Explanations

occurrences of personal pronouns and discussions involving actions or experiences

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 opportunity

-0.15

ÏİÏĤ

-0.15

 convex

-0.14

setLayout

-0.14

MBER

-0.14

 Lump

-0.14

 Tube

-0.14

occo

-0.14

haps

-0.14

ãģªãĤĭ

-0.13

POSITIVE LOGITS

ypy

0.17

hof

0.17

áºŃu

0.16

á»©

0.16

 eiusmod

0.15

ambre

0.14

Ģìŀ¥

0.14

ForMember

0.14

.camel

0.14

ANNOT

0.14

Activations Density 0.232%

occurrences of personal pronouns and discussions involving actions or experiences

No Known Activations