INDEX

Explanations

references to government committees and their activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

Ì§

-0.16

vertiser

-0.15

iotic

-0.15

 Seznam

-0.15

ijken

-0.15

.FontStyle

-0.15

Ø®ÙĪ

-0.15

ato

-0.15

nnen

-0.14

.habbo

-0.14

POSITIVE LOGITS

 Committee

0.31

 committee

0.30

 markup

0.27

 hearing

0.26

 Ranking

0.26

 Subcommittee

0.26

 Judiciary

0.24

 panel

0.24

 Ways

0.24

sub

0.23

Activations Density 0.046%

references to government committees and their activities

No Comments

No Known Activations