INDEX

Explanations

words related to food items or culinary descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ens

-0.15

alar

-0.15

eding

-0.14

 Nachricht

-0.14

ens

-0.14

ref

-0.13

ih

-0.13

 bild

-0.13

 fractional

-0.13

 crackdown

-0.13

POSITIVE LOGITS

.scalablytyped

0.18

.hw

0.17

omba

0.17

isContained

0.16

Neo

0.15

Î»ÏĮÎ³

0.15

_mB

0.15

ivery

0.14

iÐ²

0.14

intree

0.14

Activations Density 0.000%

words related to food items or culinary descriptions

No Comments

No Known Activations