INDEX

Explanations

instances of contrasting opinions or evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

etail

-0.18

icone

-0.17

mony

-0.16

riday

-0.16

ÏĨÏħ

-0.15

áº¥n

-0.15

FINE

-0.14

mj

-0.14

ledge

-0.14

agine

-0.14

POSITIVE LOGITS

 despite

0.24

 overall

0.19

 Overall

0.18

 although

0.18

 Despite

0.17

 reviewers

0.17

 spite

0.17

 Parts

0.17

 parts

0.16

 Although

0.16

Activations Density 0.020%

instances of contrasting opinions or evaluations

No Comments

No Known Activations