INDEX

Explanations

code snippets and metadata related to programming and documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ucci

-0.16

ç»¼åĲĪ

-0.15

abal

-0.15

loor

-0.15

å®Ī

-0.15

 textStyle

-0.14

lÃ¡n

-0.13

ilot

-0.13

 Diss

-0.13

orr

-0.13

POSITIVE LOGITS

 admon

0.16

Å¡ov

0.15

hta

0.15

arged

0.15

pawn

0.15

ivec

0.14

è¯ĳ

0.14

ui

0.14

rows

0.14

BCM

0.14

Activations Density 0.031%

code snippets and metadata related to programming and documentation

No Comments

No Known Activations