INDEX

Explanations

statements related to instructions or commands

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

Ã¥r

-0.16

enu

-0.16

alice

-0.15

engers

-0.15

aisy

-0.15

igo

-0.14

"crypto

-0.14

ENUM

-0.14

POSITIVE LOGITS

orr

0.17

 awakeFromNib

0.15

ouri

0.14

 Brotherhood

0.14

 indirect

0.14

Å¡ti

0.14

±Ð¾ÑĤ

0.13

 Direct

0.13

orrar

0.13

åĬ

0.13

Activations Density 0.066%

statements related to instructions or commands

No Comments

No Known Activations