INDEX

Explanations

instances of the word "associated" and its variations related to connections or relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

Ø§ÙĨÙĩ

-0.16

çĲ´

-0.15

ittel

-0.15

ãĤ¥

-0.15

 ActionTypes

-0.15

ening

-0.15

lobs

-0.15

iness

-0.15

cape

-0.15

ernet

-0.14

POSITIVE LOGITS

/un

0.16

 with

0.15

hood

0.15

ë§ŀ

0.15

unto

0.14

zl

0.14

/group

0.14

abb

0.14

ally

0.14

/op

0.13

Activations Density 0.055%

instances of the word "associated" and its variations related to connections or relationships

No Comments

No Known Activations