INDEX

Explanations

terms associated with confusion or difficulties in comprehension

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ctr

-0.23

ils

-0.22

ernity

-0.21

ishly

-0.20

cks

-0.20

azed

-0.19

ordinated

-0.19

ated

-0.18

èº«

-0.17

POSITIVE LOGITS

 actionTypes

0.16

ecko

0.16

0.15

in

0.15

OffsetTable

0.14

uzey

0.14

eza

0.14

aks

0.14

ffer

0.14

Activations Density 0.093%

terms associated with confusion or difficulties in comprehension

No Comments

No Known Activations