INDEX

Explanations

phrases related to government actions and policy decisions

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

 jadx

-0.15

 odense

-0.15

 ÑĤÐ¾Ð¶Ðµ

-0.14

 similarly

-0.14

 Bieber

-0.14

 aalborg

-0.13

 Kaepernick

-0.13

éĤ£ç§į

-0.13

Ø°ÙĦÙĥ

-0.13

ï¼ł

-0.13

POSITIVE LOGITS

0.15

↵

0.14

isce

0.14

agenta

0.14

!--

0.14

ansk

0.13

iming

0.13

 recently

0.13

Activations Density 0.622%

phrases related to government actions and policy decisions

No Comments

No Known Activations