INDEX

Explanations

activities and terms related to surfing

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

chan

-0.18

idable

-0.17

CHAN

-0.16

fortunate

-0.15

ENCH

-0.14

ignet

-0.14

udas

-0.14

 Parti

-0.14

Ãłng

-0.14

lator

-0.14

POSITIVE LOGITS

anga

0.18

ERS

0.14

 bekl

0.14

ihn

0.14

kea

0.14

DefaultValue

0.14

rose

0.14

ÄĽk

0.14

anes

0.14

Ð¸Ð½Ð¾Ð¹

0.13

Activations Density 0.010%

activities and terms related to surfing

No Comments

No Known Activations