INDEX

Explanations

programming syntax and data structure definitions

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

oya

-0.17

ointments

-0.16

oyo

-0.15

erif

-0.15

unma

-0.15

Ã¥de

-0.15

Ð²Ð°Ð¶Ð°

-0.14

ÏģÏĮ

-0.14

GuidId

-0.14

 Vice

-0.14

POSITIVE LOGITS

ilden

0.15

ulla

0.15

obsolete

0.14

_REC

0.14

jur

0.14

apus

0.14

 rady

0.14

 Darling

0.14

picture

0.13

_PID

0.13

Activations Density 0.005%

programming syntax and data structure definitions

No Comments

No Known Activations