INDEX

Explanations

the presence of specific characters or sequences within words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ager

-0.17

ce

-0.16

lane

-0.16

lag

-0.16

ne

-0.16

anna

-0.16

loff

-0.16

itage

-0.16

soever

-0.15

enced

-0.15

POSITIVE LOGITS

upal

0.17

letic

0.17

erif

0.16

Ã£i

0.15

 travÃ©s

0.14

alet

0.14

oog

0.14

resi

0.14

 partir

0.14

Ã©ro

0.14

Activations Density 0.022%

the presence of specific characters or sequences within words

No Comments

No Known Activations