INDEX

Explanations

statements regarding authority and agency in communication

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

plib

-0.15

ubl

-0.15

anzi

-0.15

åĴ²

-0.15

inand

-0.15

 sund

-0.14

alla

-0.14

Kernel

-0.14

Ð³Ð°ÑĢ

-0.14

(kernel

-0.13

POSITIVE LOGITS

plex

0.15

ann

0.14

aliz

0.14

ÃŃc

0.14

Reuse

0.14

 Keys

0.14

ques

0.13

 gest

0.13

Activations Density 0.220%

statements regarding authority and agency in communication

No Comments

No Known Activations