INDEX

Explanations

references to a comparative or alternative subject

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

imeter

-0.16

sing

-0.15

-0.14

igon

-0.14

-contact

-0.14

usz

-0.14

 Himself

-0.14

Sing

-0.14

reate

-0.13

imeters

-0.13

POSITIVE LOGITS

esium

0.17

pta

0.15

.hm

0.15

sez

0.15

 Dá»¯

0.14

oser

0.14

ITA

0.13

 Pole

0.13

èĬ¸

0.13

å¢

0.13

Activations Density 0.022%

references to a comparative or alternative subject

No Comments

No Known Activations