INDEX

Explanations

references to personal information and privacy policies

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

Hao

-0.15

ules

-0.15

stad

-0.14

uplicates

-0.14

ude

-0.14

asca

-0.14

apur

-0.14

UED

-0.14

scribe

-0.14

umas

-0.14

POSITIVE LOGITS

-Smith

0.15

 plugs

0.14

 Plug

0.14

tab

0.14

Ð²Ð°Ð¹

0.14

ookie

0.14

ÐµÑĢÑĤÐ¸

0.14

torch

0.13

ldap

0.13

 Choir

0.13

Activations Density 0.008%

references to personal information and privacy policies

No Comments

No Known Activations