INDEX

Explanations

titles of television shows or movies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

lÃ¤

-0.15

uss

-0.15

wor

-0.14

\b

-0.14

Cox

-0.13

on

-0.13

\Lib

-0.13

 irrig

-0.13

umer

-0.13

POSITIVE LOGITS

 addCriterion

0.17

tae

0.16

 empty

0.16

renom

0.16

upy

0.15

empty

0.15

ÐļÐĺ

0.15

afort

0.15

inand

0.14

-empty

0.14

Activations Density 0.049%

titles of television shows or movies

No Comments

No Known Activations