INDEX

Explanations

phrases that indicate comparisons between entities or concepts

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

Not in Any Lists

No Comments

Negative Logits

ik

-0.15

 WHETHER

-0.14

OutOf

-0.14

imar

-0.14

abay

-0.14

ship

-0.14

hana

-0.13

ka

-0.13

ful

-0.13

 exactly

-0.13

POSITIVE LOGITS

atest

0.16

Mig

0.15

quam

0.14

à¸©

0.14

á»įc

0.14

vez

0.14

ilers

0.14

ufs

0.14

odore

0.14

ools

0.14

Activations Density 0.039%

phrases that indicate comparisons between entities or concepts

No Comments

No Known Activations