INDEX

Explanations

sentiments related to social perceptions and identities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ulet

-0.15

 à¹Ģà¸Ĥà¸ķ

-0.14

 é£

-0.14

pie

-0.14

laden

-0.14

lÄ±k

-0.14

stup

-0.14

indh

-0.14

iani

-0.14

emark

-0.13

POSITIVE LOGITS

oyo

0.17

0.16

Station

0.14

 tinder

0.14

zw

0.14

 NavController

0.14

cken

0.14

arsers

0.14

Activations Density 0.335%

sentiments related to social perceptions and identities

No Comments

No Known Activations