INDEX

Explanations

expressions of high emotional intensity or strong opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ibar

-0.17

vie

-0.16

ovable

-0.15

logen

-0.15

ailer

-0.14

onso

-0.14

leta

-0.14

reira

-0.14

efe

-0.14

adoo

-0.14

POSITIVE LOGITS

Pros

0.20

 pros

0.17

 Pros

0.17

 Overall

0.15

ajs

0.15

 overall

0.15

Aws

0.14

âĢı

0.14

overall

0.14

íĺ¼

0.14

Activations Density 0.043%

expressions of high emotional intensity or strong opinions

No Comments

No Known Activations