INDEX

Explanations

references to names and numerical identifiers, likely focusing on individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ÐĵÐŀ

-0.17

{text

-0.16

zsche

-0.15

urma

-0.15

verity

-0.14

áº¿t

-0.14

å¾ħ

-0.14

osta

-0.14

ankan

-0.14

ffer

-0.14

POSITIVE LOGITS

aghan

0.18

pons

0.15

arine

0.15

Ãµes

0.15

 Griff

0.15

ìłĿ

0.14

ato

0.14

ATO

0.14

ajax

0.14

Activations Density 0.487%

references to names and numerical identifiers, likely focusing on individuals or entities

No Comments

No Known Activations