INDEX

Explanations

references to the reader and their involvement or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

oref

-0.16

_Impl

-0.15

ufs

-0.15

ildren

-0.14

gan

-0.14

tml

-0.14

 Ð¾Ð±Ð¾ÑĢ

-0.14

 å¾Ĵ

-0.14

incer

-0.14

ailles

-0.13

POSITIVE LOGITS

ths

0.19

 deserve

0.17

Des

0.16

 deserves

0.16

dao

0.15

Des

0.15

 dreams

0.15

Version

0.15

may

0.14

 dream

0.14

Activations Density 0.084%

references to the reader and their involvement or actions

No Comments

No Known Activations