INDEX

Explanations

specific dates and months referenced in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

amat

-0.16

Rog

-0.16

aven

-0.16

alli

-0.16

hab

-0.16

 prec

-0.16

 Industrial

-0.15

ohana

-0.15

 industrial

-0.15

vas

-0.15

POSITIVE LOGITS

0.16

walls

0.15

	throws

0.15

oldur

0.14

 defaultMessage

0.14

.LoadScene

0.14

 Sesso

0.14

camp

0.14

BUM

0.14

victim

0.14

Activations Density 0.054%

specific dates and months referenced in the text

No Comments

No Known Activations