INDEX

Explanations

timestamps and time-related information

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

alie

-0.17

rug

-0.15

letcher

-0.15

ÑĥÑĤÐ¸

-0.14

efeller

-0.14

Ð°ÑĤÑĥ

-0.14

(æľĪ

-0.14

dorf

-0.13

hurst

-0.13

 Caller

-0.13

POSITIVE LOGITS

Slf

0.15

à¸¶à¸ģ

0.14

uesta

0.14

 Working

0.14

verbatim

0.14

Ãªm

0.13

Ã¦r

0.13

å¹

0.13

VML

0.13

Activations Density 0.022%

timestamps and time-related information

No Comments

No Known Activations

timestamps and time-related information

No Comments

No Known Activations