INDEX

Explanations

references to major wars, particularly World Wars I and II

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ikan

-0.18

uture

-0.16

ated

-0.15

IES

-0.15

ollapsed

-0.14

 Mile

-0.14

ÑĤÐ¾Ð³Ð¾

-0.14

 Dish

-0.14

estroy

-0.14

.Authentication

-0.14

POSITIVE LOGITS

-era

0.17

UED

0.15

arro

0.15

/umd

0.14

çį²

0.14

blings

0.14

ble

0.13

_DECLS

0.13

çĽ®ãģ®

0.13

Activations Density 0.007%

references to major wars, particularly World Wars I and II

No Comments

No Known Activations