INDEX

Explanations

terms related to a specific video streaming service or related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

lops

-0.18

arios

-0.17

veau

-0.15

omu

-0.15

umas

-0.14

riding

-0.14

atcher

-0.14

ech

-0.14

lop

-0.14

POSITIVE LOGITS

Ã©o

0.18

EOS

0.18

oucÃŃ

0.17

hya

0.16

ertino

0.15

entes

0.15

ÐµÐ¾

0.15

à¸µà¹Ĥà¸Ń

0.15

agra

0.15

blr

0.15

Activations Density 0.012%

terms related to a specific video streaming service or related content

No Comments

No Known Activations

terms related to a specific video streaming service or related content

No Comments

No Known Activations