INDEX

Explanations

terms related to moral superiority and condescension

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

estre

-0.19

uddle

-0.16

ÙĬØ¬

-0.15

estro

-0.14

META

-0.14

eurs

-0.14

buster

-0.14

jh

-0.14

iage

-0.14

 Pioneer

-0.13

POSITIVE LOGITS

_:*

0.17

EMU

0.15

elly

0.14

CHANT

0.14

Gim

0.14

gate

0.14

 Cena

0.14

osten

0.14

Activations Density 0.191%

terms related to moral superiority and condescension

No Comments

No Known Activations