INDEX

Explanations

references to the reader or the self in a personal context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

Ð³Ð°ÑĢ

-0.20

\Schema

-0.16

YLON

-0.15

 Emerald

-0.15

WN

-0.15

 cáºŃn

-0.14

intColor

-0.14

VERSE

-0.14

Ð´Ñĥ

-0.14

inent

-0.14

POSITIVE LOGITS

elsea

0.17

 Hack

0.16

pos

0.15

upp

0.15

rete

0.14

iones

0.14

 previously

0.13

 recently

0.13

len

0.13

Hack

0.13

Activations Density 0.047%

references to the reader or the self in a personal context

No Comments

No Known Activations