INDEX

Explanations

references to a proven history of success or achievement

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

 contacted

-0.16

Mag

-0.15

 contact

-0.15

à¸µà¸Ķ

-0.14

 Misc

-0.14

orf

-0.14

oti

-0.14

erli

-0.14

èģĶç³»

-0.13

POSITIVE LOGITS

 nackte

0.16

Ã¨n

0.15

_CS

0.15

IZES

0.15

ivet

0.15

ouser

0.14

ctrine

0.14

à¸ģà¸²à¸£à¸ŀ

0.14

reeNode

0.14

iry

0.14

Activations Density 0.007%

references to a proven history of success or achievement

No Comments

No Known Activations