INDEX

Explanations

references to data structures or variables in code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

irie

-0.16

ypy

-0.14

omb

-0.14

/mit

-0.14

amura

-0.13

oyer

-0.13

icari

-0.13

 $("#"

-0.13

 cris

-0.13

atri

-0.13

POSITIVE LOGITS

.RunWith

0.15

ë³Ħ

0.15

/Area

0.15

ValuePair

0.14

.rollback

0.14

usize

0.14

ãģļ

0.14

Ø¹Ø¨

0.13

.choices

0.13

 addCriterion

0.13

Activations Density 0.593%

references to data structures or variables in code snippets

No Comments

No Known Activations