INDEX

Explanations

connections represented by conjunctions in phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

.getvalue

-0.15

urg

-0.15

isu

-0.14

 aggress

-0.14

rez

-0.14

opleft

-0.13

 injunction

-0.13

ZD

-0.13

ilo

-0.13

POSITIVE LOGITS

/or

0.22

para

0.18

 semi

0.17

rog

0.17

ific

0.17

Passwords

0.16

 otherwise

0.16

rogen

0.15

 para

0.15

BITS

0.14

Activations Density 0.175%

connections represented by conjunctions in phrases

No Comments

No Known Activations