INDEX

Explanations

temporal references and indicators of time 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 @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

Ã©ry

-0.18

otta

-0.16

 Appropri

-0.15

opus

-0.15

aus

-0.15

elman

-0.14

anne

-0.14

atten

-0.14

anan

-0.14

amon

-0.14

POSITIVE LOGITS

orate

0.18

FromClass

0.16

ExecutionContext

0.15

vest

0.14

ndern

0.14

ethod

0.14

StatusLabel

0.14

ãĥķãĥĪ

0.13

 setC

0.13

icolor

0.13

Activations Density 0.305%

temporal references and indicators of time in the text

No Comments

No Known Activations