INDEX

Explanations

references to physical locations and objects in the narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

modifiable

-0.16

adders

-0.15

phia

-0.15

quier

-0.14

:\"

-0.14

-0.13

.mutable

-0.13

£½

-0.13

ijken

-0.13

POSITIVE LOGITS

apper

0.14

ÐºÑĢÐ°ÑĹ

0.14

èĤ²

0.14

ListComponent

0.13

amba

0.13

odel

0.13

’ÑĶ

0.12

eward

0.12

alyzed

0.12

 Morrow

0.12

Activations Density 0.223%

references to physical locations and objects in the narrative

No Comments

No Known Activations