INDEX

Explanations

references to legal cases or precedents

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

oints

-0.15

arlar

-0.15

spo

-0.14

Ø§ÛĮØ§ÙĨ

-0.14

Torrent

-0.14

ignon

-0.14

rieg

-0.14

ÐµÐ²Ð¾Ð¹

-0.14

bourg

-0.14

asic

-0.14

POSITIVE LOGITS

0.15

çĺ

0.15

 predecessor

0.14

 punches

0.14

Ð½ÑĸÑģÑĤ

0.13

ochen

0.13

arrow

0.13

enan

0.13

achi

0.13

berry

0.13

Activations Density 0.089%

references to legal cases or precedents

No Comments

No Known Activations