INDEX

Explanations

instances of conditional phrases indicating 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 @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

bedo

-0.16

adera

-0.16

sburg

-0.15

sville

-0.15

bole

-0.15

itra

-0.15

inas

-0.15

undra

-0.15

swick

-0.15

nant

-0.14

POSITIVE LOGITS

 pier

0.16

 piercing

0.14

 Harvey

0.14

 corner

0.13

ota

0.13

else

0.13

/loader

0.13

 else

0.13

 wrapper

0.13

 Motion

0.13

Activations Density 0.009%

instances of conditional phrases indicating hypothetical scenarios

No Comments

No Known Activations