INDEX

Explanations

references to legal terms and government bodies, particularly related to Congress and injunctions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ritz

-0.15

$core

-0.15

[js

-0.14

osate

-0.14

.updateDynamic

-0.14

nave

-0.14

ÙĨØ¯ÛĮ

-0.14

ettel

-0.14

caption

-0.14

 Ð¾ÐºÐ¾Ð½

-0.14

POSITIVE LOGITS

rat

0.17

oleon

0.17

NC

0.17

elon

0.16

 Crosby

0.15

Ø§Øµ

0.15

asz

0.15

elo

0.14

sel

0.14

ides

0.14

Activations Density 0.011%

references to legal terms and government bodies, particularly related to Congress and injunctions

No Comments

No Known Activations