INDEX

Explanations

instances of the word "down" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

oston

-0.16

mons

-0.15

olars

-0.15

ÑĢÐµÐ»

-0.15

zioni

-0.15

Ð¾ÐºÐ¾Ð½

-0.14

 miá»ĩng

-0.14

apult

-0.14

ormsg

-0.14

Ã¬m

-0.14

POSITIVE LOGITS

emann

0.17

rez

0.15

 Becker

0.15

eza

0.15

inion

0.15

uter

0.15

 McMahon

0.14

éĺµ

0.14

ois

0.14

ervisor

0.14

Activations Density 0.029%

instances of the word "down" and its variations

No Comments

No Known Activations