INDEX

Explanations

code-related terms or keywords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 redund

-0.20

webs

-0.17

 redundancy

-0.17

amo

-0.15

CharacterSet

-0.15

ety

-0.15

ç«ľ

-0.14

ability

-0.14

 Ð¿ÐµÑĢÐµÐ³

-0.14

amar

-0.14

POSITIVE LOGITS

ilos

0.16

acier

0.16

ÑĮ

0.15

arend

0.15

ĸī

0.15

yon

0.15

aron

0.15

erosis

0.13

ifold

0.13

.removeAttribute

0.13

Activations Density 0.001%

code-related terms or keywords

No Comments

No Known Activations