INDEX

Explanations

cooking instructions related to browning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

anzi

-0.16

-0.15

hood

-0.15

eree

-0.14

 Railroad

-0.14

ital

-0.14

 duty

-0.14

apel

-0.14

 seins

-0.14

POSITIVE LOGITS

_mes

0.17

 derec

0.17

ï»¿#

0.17

lify

0.15

afen

0.15

ÏįÎ½

0.14

ldb

0.14

ĶåĽŀ

0.14

erosis

0.14

Ãµi

0.14

Activations Density 0.014%

cooking instructions related to browning

No Comments

No Known Activations