INDEX

Explanations

references to the physical attributes and characteristics of objects or items

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

tran

-0.16

ãĥªãĤ«

-0.15

alfa

-0.15

hang

-0.15

 Carroll

-0.15

ulis

-0.15

rief

-0.14

funcs

-0.14

hlen

-0.14

POSITIVE LOGITS

 inside

0.18

core

0.18

/Core

0.18

-core

0.17

/core

0.17

CORE

0.17

oram

0.16

 core

0.16

orum

0.15

 cores

0.15

Activations Density 0.120%

references to the physical attributes and characteristics of objects or items

No Comments

No Known Activations