INDEX

Explanations

mentions of things or people that are frequently neglected or not adequately recognized

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ï¸

-0.16

iaz

-0.16

ãĤ«ãĥ¼

-0.15

stad

-0.14

estion

-0.14

_UNSUPPORTED

-0.14

ÙĬÙĨÙĩ

-0.14

AZE

-0.14

 opposite

-0.14

POSITIVE LOGITS

ablish

0.16

Ð²Ð°Ð¶

0.15

ibaba

0.15

amax

0.15

adoo

0.15

 Gems

0.15

 Madden

0.14

Ã©k

0.14

_calibration

0.14

atabase

0.14

Activations Density 0.030%

mentions of things or people that are frequently neglected or not adequately recognized

No Comments

No Known Activations