INDEX

Explanations

references to specific volumes and editions of works or publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ecom

-0.16

 å§

-0.16

 hands

-0.15

ONS

-0.15

ouri

-0.15

mo

-0.15

-0.14

inn

-0.14

allest

-0.14

Ø§ÙĦØ¯

-0.14

POSITIVE LOGITS

à¤¾à¤ķà¤°

0.16

enia

0.15

åģ¥

0.14

setType

0.14

TestCategory

0.14

ActivityResult

0.14

hog

0.14

 dÃ¢n

0.13

APPER

0.13

Activations Density 0.030%

references to specific volumes and editions of works or publications

No Comments

No Known Activations