INDEX

Explanations

references to data storage and programming elements in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

-0.17

soo

-0.15

 familiar

-0.15

his

-0.14

 reality

-0.14

:)

-0.14

gro

-0.14

ahl

-0.14

 regular

-0.13

POSITIVE LOGITS

 ÅĻÃŃj

0.18

ì§ĵ

0.16

odic

0.15

.synthetic

0.14

ãģıãģł

0.14

íĨ

0.14

 prÅ¯bÄĽhu

0.14

 Bloody

0.14

DBG

0.14

AREST

0.14

Activations Density 0.015%

references to data storage and programming elements in code

No Comments

No Known Activations