INDEX

Explanations

references to legal proceedings and guilty pleas related to criminal charges

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

abase

-0.18

nett

-0.17

 Ø²Ùħ

-0.16

itzer

-0.15

aso

-0.15

pager

-0.14

rnd

-0.14

èĩ´

-0.14

beth

-0.14

_recovery

-0.14

POSITIVE LOGITS

ple

0.46

Ple

0.46

 plea

0.42

 pleas

0.41

ple

0.41

PLE

0.35

 pleaded

0.32

 plead

0.32

 pleading

0.32

 guilty

0.28

Activations Density 0.032%

references to legal proceedings and guilty pleas related to criminal charges

No Comments

No Known Activations