INDEX

Explanations

geographical locations and park-related references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

Ð¿Ð¾Ð²ÑĸÐ´

-0.16

.values

-0.16

iyim

-0.15

Ã¢u

-0.15

à¥įà¤µà¤µ

-0.15

Helmet

-0.15

_BLOCKS

-0.14

:CGRect

-0.14

 vals

-0.14

PickerController

-0.14

POSITIVE LOGITS

 roller

0.15

chin

0.15

orical

0.14

ory

0.14

Gim

0.13

fak

0.13

urrences

0.13

ported

0.13

/repository

0.13

esso

0.13

Activations Density 0.197%

geographical locations and park-related references

No Comments

No Known Activations