INDEX

Explanations

terms and concepts indicating legal or procedural implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ander

-0.16

ango

-0.16

orts

-0.15

ÏĦÏĥÎ¹

-0.14

enschaft

-0.14

 bail

-0.14

 travel

-0.13

piler

-0.13

 Carr

-0.13

POSITIVE LOGITS

AREST

0.17

fold

0.14

 táºŃn

0.14

Sc

0.14

alion

0.14

 Ø£Ø¬

0.14

Â¥

0.14

poser

0.14

)\<

0.14

chner

0.13

Activations Density 0.027%

terms and concepts indicating legal or procedural implications

No Comments

No Known Activations