INDEX

Explanations

references to legal professionals and legal institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

alf

-0.16

 corner

-0.14

 tongue

-0.14

zik

-0.14

 hang

-0.14

iere

-0.14

alfa

-0.14

ihan

-0.14

Luk

-0.14

iche

-0.14

POSITIVE LOGITS

0.16

Probe

0.16

ISOString

0.15

(fullfile

0.15

getKey

0.14

rios

0.14

 Observer

0.14

olist

0.14

Ĳ

0.14

rets

0.14

Activations Density 0.063%

references to legal professionals and legal institutions

No Comments

No Known Activations