INDEX

Explanations

punctuation marks, particularly quotation marks

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

mmo

-0.15

æĬĺ

-0.14

ante

-0.14

mess

-0.14

 denominator

-0.14

CCA

-0.14

ï»¿

-0.14

 challenger

-0.14

REEN

-0.13

POSITIVE LOGITS

Ø¯Ø§ÙĨ

0.16

tracer

0.15

acer

0.15

urar

0.15

ä¹³

0.14

overs

0.14

utsch

0.13

lox

0.13

pole

0.13

orer

0.13

Activations Density 0.074%

punctuation marks, particularly quotation marks

No Comments

No Known Activations