INDEX

Explanations

recognition and references to classic literature and notable novels

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

inkel

-0.17

ÑĥÑģÐ°

-0.16

ÅĻe

-0.15

-0.14

 Stock

-0.14

vrier

-0.14

apist

-0.14

UA

-0.14

POSITIVE LOGITS

 novel

0.22

 novels

0.19

Attachments

0.17

 Sidd

0.16

The

0.16

Interpreter

0.15

/movie

0.15

 Convers

0.15

 Fahrenheit

0.15

à¸§à¸Ļ

0.15

Activations Density 0.187%

recognition and references to classic literature and notable novels

No Comments

No Known Activations