INDEX

Explanations

references to collaborative progress and adjustments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

nen

-0.15

haus

-0.14

 cÃ¢u

-0.14

isten

-0.14

igu

-0.13

hog

-0.13

ossa

-0.13

ague

-0.13

 descending

-0.13

ÐµÐºÐ°

-0.13

POSITIVE LOGITS

 scope

0.19

scope

0.18

 stakes

0.18

 size

0.17

 coverage

0.16

coverage

0.16

 number

0.15

WithError

0.15

 Resolution

0.15

ÄĽt

0.15

Activations Density 0.186%

references to collaborative progress and adjustments

No Comments

No Known Activations