INDEX

Explanations

references to fresh or healthy food ingredients

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

Bean

-0.19

-0.16

-0.15

Builder

-0.14

 Garrison

-0.14

orca

-0.14

 insulting

-0.14

yz

-0.14

POSITIVE LOGITS

à¸ªà¸Ķ

0.17

 grown

0.17

skins

0.15

 rá»«ng

0.15

 skins

0.15

 flown

0.15

swith

0.15

OKIE

0.15

ÙĬØ«

0.14

gie

0.14

Activations Density 0.067%

references to fresh or healthy food ingredients

No Comments

No Known Activations