INDEX

Explanations

symbols and formatting elements typically used in code or markup languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

alance

-0.15

 Vict

-0.15

iferay

-0.15

uper

-0.14

 Downing

-0.14

roadcast

-0.14

tic

-0.14

vale

-0.14

tie

-0.14

POSITIVE LOGITS

br

0.17

oksen

0.16

br

0.15

emd

0.15

ollo

0.15

BR

0.15

 McCart

0.14

Ð¾Ð»Ð¾

0.14

odus

0.14

ocal

0.14

Activations Density 0.445%

symbols and formatting elements typically used in code or markup languages

No Comments

No Known Activations