INDEX

Explanations

legal terminology related to liability and warranties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ifa

-0.16

iasm

-0.16

 ADDRESS

-0.14

ampo

-0.14

inston

-0.14

 THROW

-0.14

opsis

-0.13

ote

-0.13

.Experimental

-0.13

 ÑģÑĤÐ°Ð²

-0.13

POSITIVE LOGITS

enderit

0.16

 Tort

0.16

 unnamed

0.15

 TORT

0.15

 tort

0.15

↵ ↵

0.15

ColumnsMode

0.14

unp

0.14

ModifiedDate

0.14

-toggler

0.14

Activations Density 0.009%

legal terminology related to liability and warranties

No Comments

No Known Activations