INDEX

Explanations

terms related to user-generated content platforms and their components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

zac

-0.15

entin

-0.15

grese

-0.14

leccion

-0.14

UILTIN

-0.14

aversable

-0.14

aire

-0.14

nees

-0.14

 nues

-0.14

MOTE

-0.14

POSITIVE LOGITS

 latter

0.23

NamedQuery

0.15

eniable

0.14

Zar

0.14

zeit

0.14

isz

0.14

Ð°ÑĢÑĸÐ²

0.13

license

0.13

olan

0.13

Activations Density 1.000%

terms related to user-generated content platforms and their components

No Comments

No Known Activations