INDEX

Explanations

phrases that reflect support and enthusiasm from individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ÑĨÐµ

-0.17

bbe

-0.17

æ°¸ä¹ħ

-0.16

iare

-0.15

ylon

-0.15

ocz

-0.15

PLL

-0.14

glomer

-0.14

_AX

-0.14

registry

-0.14

POSITIVE LOGITS

eki

0.15

ice

0.15

 among

0.15

_pagination

0.14

by

0.14

ingly

0.14

 amongst

0.14

 widespread

0.14

 Kaiser

0.14

Activations Density 0.141%

phrases that reflect support and enthusiasm from individuals or groups

No Comments

No Known Activations