INDEX

Explanations

terms related to geographical locations and significant events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

glomer

-0.15

Gio

-0.15

.runners

-0.14

ÌĨ

-0.14

letic

-0.14

enthal

-0.14

ongs

-0.14

ently

-0.13

ucch

-0.13

emia

-0.13

POSITIVE LOGITS

anco

0.17

0.15

ÑĩÐ¸Ðº

0.15

Ð¤ÐĽ

0.15

 Becker

0.13

 bottle

0.13

_decrypt

0.13

sc

0.13

.Exception

0.13

 bottles

0.13

Activations Density 0.026%

terms related to geographical locations and significant events

No Comments

No Known Activations