INDEX

Explanations

symbols and punctuation used in context

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

 Hollow

-0.16

udoku

-0.15

á»£i

-0.15

ÃŁen

-0.15

Øµ

-0.15

osyal

-0.15

Ð¾Ð¼ÐµÑĤ

-0.15

ÏĪÎµ

-0.14

ibling

-0.14

 Ð¶Ðµ

-0.14

POSITIVE LOGITS

/-

0.18

chein

0.17

oller

0.16

ams

0.16

apo

0.15

++++++++++++++++

0.15

apol

0.14

amp

0.14

apos

0.14

 vanity

0.14

Activations Density 0.016%

symbols and punctuation used in context

No Comments

No Known Activations