INDEX

Explanations

phrases that indicate conditional situations or hypothetical scenarios

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

ÛĮÙĨÙĩ

-0.15

eger

-0.15

ussen

-0.15

 indeed

-0.14

BITS

-0.14

infeld

-0.14

issors

-0.14

yas

-0.14

enville

-0.13

.nasa

-0.13

POSITIVE LOGITS

reon

0.17

 Vital

0.15

fst

0.14

à¥įà¤¸à¤°

0.14

itious

0.14

imiento

0.14

adata

0.14

 protector

0.13

ĵ

0.13

.ser

0.13

Activations Density 0.041%

phrases that indicate conditional situations or hypothetical scenarios

No Comments

No Known Activations