INDEX

Explanations

phrases related to regulations and guidelines applicable to various entities or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

(.)

-0.16

_ASSUME

-0.15

ÐºÑĥÑĢ

-0.15

erin

-0.14

/client

-0.14

 Burr

-0.14

fixed

-0.14

_FIXED

-0.14

á»ĥm

-0.14

ger

-0.14

POSITIVE LOGITS

0.16

rist

0.14

ESA

0.14

think

0.14

Â«

0.13

 malÃ©

0.13

yet

0.13

 mens

0.13

Activations Density 0.260%

phrases related to regulations and guidelines applicable to various entities or groups

No Comments

No Known Activations