INDEX

Explanations

terms related to evaluation or accountability

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

-0.20

ones

-0.19

-0.17

the

-0.17

 ones

-0.17

-0.16

-0.15

 punch

-0.15

POSITIVE LOGITS

ï»¿#

0.21

HeaderCode

0.20

'gc

0.19

NewProp

0.18

GuidId

0.18

_vlog

0.18

endcode

0.17

ï»¿using

0.17

togroup

0.16

RuntimeObject

0.16

Activations Density 0.631%

terms related to evaluation or accountability

No Comments

No Known Activations