INDEX

Explanations

titles of movies and their specific details or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

/stdc

-0.15

apers

-0.14

Selectors

-0.14

ãĥ³ãĤ¬

-0.14

 Navy

-0.14

owania

-0.14

 onstage

-0.13

iminal

-0.13

ifu

-0.13

Supply

-0.13

POSITIVE LOGITS

 ActiveSupport

0.18

tele

0.17

 tele

0.16

 Channel

0.16

acin

0.16

 grain

0.15

Tro

0.15

 adaptations

0.15

 ØªÙĦÙĪÛĮØ²ÛĮ

0.15

 Cord

0.15

Activations Density 0.109%

titles of movies and their specific details or events

No Comments

No Known Activations