INDEX

Explanations

references to significant concepts and terms related to documents and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ardon

-0.15

letic

-0.15

etros

-0.15

Å¡t

-0.14

vos

-0.14

vo

-0.14

ÑĢÐ¸Ð³

-0.14

rowing

-0.14

pic

-0.14

asm

-0.14

POSITIVE LOGITS

opher

0.15

awe

0.15

inkel

0.14

celik

0.14

 Mann

0.14

 Lamp

0.14

Fri

0.14

AN

0.14

iki

0.13

ungi

0.13

Activations Density 0.009%

references to significant concepts and terms related to documents and their characteristics

No Comments

No Known Activations