INDEX

Explanations

references to historical events and figures, particularly in American history

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

GBT

-0.15

bol

-0.15

ÑģÑĤÑĭ

-0.15

nika

-0.14

_pool

-0.14

ollo

-0.14

pective

-0.14

 pool

-0.14

ÅĪ

-0.13

 Giang

-0.13

POSITIVE LOGITS

ANTLR

0.15

 pupper

0.15

_rq

0.14

ÐĲÑĢÑħÑĸÐ²

0.14

olon

0.14

Civ

0.14

issan

0.14

 Sever

0.13

-NLS

0.13

akens

0.13

Activations Density 0.404%

references to historical events and figures, particularly in American history

No Comments

No Known Activations