INDEX

Explanations

references to specific media titles and their associated attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ilan

-0.14

ableViewController

-0.14

antz

-0.14

Ð¾Ð¶Ð´ÐµÐ½Ð¸Ðµ

-0.13

opc

-0.13

.Îł

-0.13

éł

-0.13

ooth

-0.13

ocal

-0.13

oke

-0.13

POSITIVE LOGITS

 Bolt

0.14

ushima

0.14

EDGE

0.14

 synonyms

0.14

LTR

0.14

ayet

0.14

apest

0.14

agens

0.13

.subscriptions

0.13

Activations Density 0.005%

references to specific media titles and their associated attributes

No Comments

No Known Activations