INDEX

Explanations

references to location or spatial context

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

ula

-0.22

resse

-0.15

IDER

-0.15

ULA

-0.14

quier

-0.14

_SID

-0.14

ãĤ¹ãĤ¯

-0.14

)(__

-0.14

urr

-0.14

ç¹Ķ

-0.14

POSITIVE LOGITS

rike

0.16

cales

0.15

rio

0.15

Rat

0.15

amily

0.14

alet

0.14

åĿĬ

0.14

stdClass

0.14

 Homo

0.13

Activations Density 0.167%

references to location or spatial context

No Comments

No Known Activations