INDEX

Explanations

entities related to media production and publication

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

-0.15

positor

-0.15

 Dove

-0.14

hos

-0.14

 ratios

-0.14

olumn

-0.14

andal

-0.14

 ratio

-0.13

 driven

-0.13

ern

-0.13

POSITIVE LOGITS

otime

0.15

IRO

0.14

argout

0.14

orget

0.14

lerce

0.14

uche

0.14

ivos

0.14

ìĸ´ëĤĺ

0.14

Ð°Ð»Ð¾

0.13

Activations Density 0.030%

entities related to media production and publication

No Comments

No Known Activations