INDEX

Explanations

punctuation marks, particularly semicolons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

iddi

-0.18

ddb

-0.17

IMPLEMENT

-0.16

letion

-0.16

allet

-0.15

ippet

-0.15

ylko

-0.15

Î¾Î¹

-0.14

ysl

-0.14

enis

-0.13

POSITIVE LOGITS

ered

0.17

ÏĥÎ·

0.15

Å¾e

0.15

ergic

0.14

ITA

0.14

rahim

0.14

 æ¹

0.14

áº¯c

0.13

iba

0.13

probe

0.13

Activations Density 0.090%

punctuation marks, particularly semicolons

No Comments

No Known Activations