INDEX

Explanations

code snippets and programming structures

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

 retract

-0.15

ikip

-0.14

orth

-0.14

Ð¾Ð»Ð¾Ð²

-0.14

.TestTools

-0.14

Ã¡cil

-0.13

sl

-0.13

ibil

-0.13

anja

-0.13

ault

-0.13

POSITIVE LOGITS

igu

0.17

XS

0.15

PDOException

0.15

 sobie

0.14

dddd

0.14

efore

0.14

abela

0.14

_SB

0.14

-LAST

0.14

UTE

0.14

Activations Density 0.029%

code snippets and programming structures

No Comments

No Known Activations