INDEX

Explanations

assignments and references in code, particularly involving arrays and pointers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

lator

-0.16

ucas

-0.15

ter

-0.14

lington

-0.14

ussian

-0.14

mand

-0.14

ness

-0.14

pery

-0.14

ibil

-0.13

ĸ

-0.13

POSITIVE LOGITS

0.16

ÄĽk

0.15

zt

0.15

invisible

0.14

è¦³

0.14

 invis

0.14

otive

0.14

Ton

0.14

ucht

0.13

apus

0.13

Activations Density 0.294%

assignments and references in code, particularly involving arrays and pointers

No Comments

No Known Activations