INDEX

Explanations

references to specific furniture items and their characteristics

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

borg

-0.19

 reform

-0.15

eparator

-0.14

ķĮ

-0.14

'=>"

-0.13

à¥Ģà¤¶

-0.13

 Erect

-0.13

ãĥ³ãĥĳ

-0.13

 wire

-0.13

ãĥ³ãĥĶ

-0.13

POSITIVE LOGITS

itness

0.16

ãĥĲãĥ¼

0.14

boo

0.14

jom

0.14

Tu

0.14

ories

0.13

elin

0.13

 klik

0.13

zl

0.13

Activations Density 0.026%

references to specific furniture items and their characteristics

No Comments

No Known Activations