INDEX

Explanations

references to specific television shows and their details

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

anse

-0.17

spe

-0.16

scala

-0.15

askell

-0.15

 Ð¿Ð¾Ð¼

-0.15

agnet

-0.14

Ø¬ÙĨ

-0.14

selectAll

-0.13

POSITIVE LOGITS

 runaway

0.17

ereal

0.16

igar

0.16

ÑģÐ¾Ð½

0.15

-env

0.14

ENG

0.14

THON

0.14

IGHLIGHT

0.14

 Panel

0.14

¶Į

0.14

Activations Density 0.011%

references to specific television shows and their details

No Comments

No Known Activations