INDEX

Explanations

references to feeding or food-related actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ogl

-0.16

opus

-0.15

heit

-0.15

epad

-0.15

ophon

-0.14

ity

-0.14

 Ð²ÐµÐ´ÑĮ

-0.14

ely

-0.14

 Klopp

-0.14

ue

-0.14

POSITIVE LOGITS

/feed

0.21

-feed

0.19

.feed

0.16

/drivers

0.16

ruary

0.15

è¡Ĩ

0.15

rought

0.15

 uá»ĳng

0.14

_feed

0.14

linkplain

0.14

Activations Density 0.028%

references to feeding or food-related actions

No Comments

No Known Activations