INDEX

Explanations

identifications of people and their roles in official contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

andom

-0.15

iom

-0.15

FD

-0.14

Ä±cÄ±

-0.14

undi

-0.14

Ð¾Ð¶Ð´ÐµÐ½Ð¸Ñı

-0.14

etes

-0.14

uu

-0.14

ierre

-0.14

icc

-0.13

POSITIVE LOGITS

uzzi

0.15

.nlm

0.14

atile

0.14

.twitch

0.14

ToLower

0.14

ividad

0.14

arasÄ±

0.14

.NewLine

0.14

aghan

0.14

chal

0.14

Activations Density 0.027%

identifications of people and their roles in official contexts

No Comments

No Known Activations