INDEX

Explanations

references to locations or questions about places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Hanson

-0.18

ulla

-0.16

ki

-0.15

æĮ¯

-0.14

GP

-0.14

 Ting

-0.14

tings

-0.14

xing

-0.14

set

-0.14

POSITIVE LOGITS

ãĥ¼ãĥľ

0.16

avit

0.16

ÅĻel

0.16

 else

0.15

 Ð½Ð°Ð¹Ð±

0.15

ncia

0.15

TF

0.14

Ð¾ÑıÐ½

0.14

eturn

0.14

 æ¶

0.14

Activations Density 0.035%

references to locations or questions about places

No Comments

No Known Activations