INDEX

Explanations

instances of the word "talk" and its variants, indicating a focus on conversation or communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

icari

-0.16

enschaft

-0.16

©

-0.15

ez

-0.15

bat

-0.14

ment

-0.14

BorderStyle

-0.14

-bodied

-0.14

ÑĸÑĤ

-0.14

MENT

-0.14

POSITIVE LOGITS

 about

0.20

-about

0.18

 despre

0.17

about

0.17

ative

0.16

 About

0.15

 ABOUT

0.15

About

0.15

Î¹

0.15

ableObject

0.15

Activations Density 0.050%

instances of the word "talk" and its variants, indicating a focus on conversation or communication

No Comments

No Known Activations