INDEX

Explanations

references to critical issues or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

olina

-0.15

etak

-0.15

ef

-0.15

ok

-0.15

aim

-0.15

imax

-0.15

Ð¸ÑĤÐ¾Ð¼

-0.15

ubi

-0.15

ihan

-0.14

ipur

-0.14

POSITIVE LOGITS

ritical

0.15

_critical

0.15

 Critical

0.15

izzie

0.15

 critical

0.14

otta

0.14

Critical

0.14

ieÅ¼

0.14

typeof

0.14

éĤª

0.13

Activations Density 0.012%

references to critical issues or conditions

No Comments

No Known Activations