INDEX

Explanations

phrases indicating sequential actions or events

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ivan

-0.15

postalcode

-0.14

aker

-0.14

 compar

-0.14

igr

-0.14

olt

-0.13

eba

-0.13

_EMIT

-0.13

POSITIVE LOGITS

ipay

0.17

ings

0.17

azar

0.17

oad

0.16

Voj

0.16

noon

0.15

meldung

0.15

inÃ§

0.14

 Stap

0.14

agger

0.14

Activations Density 0.018%

phrases indicating sequential actions or events

No Known Activations