INDEX

Explanations

textual representations of names, titles, and possibly other identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

/inet

-0.18

 Brut

-0.16

@js

-0.16

lamaz

-0.15

-www

-0.15

Ã¼t

-0.15

ÑĤÐ°Ð¶

-0.15

ÑĢÐ¾Ð¹

-0.14

bau

-0.14

 WaitForSeconds

-0.14

POSITIVE LOGITS

ker

0.18

ker

0.17

Ker

0.17

KER

0.16

 siÃ¨

0.16

Stat

0.16

 norms

0.16

.com

0.15

stat

0.15

Activations Density 0.006%

textual representations of names, titles, and possibly other identifiers

No Comments

No Known Activations