INDEX

Explanations

references to self in method calls or object properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

Zd

-0.16

.setAdapter

-0.14

leh

-0.14

à¸²à¸

-0.14

 Euras

-0.14

((*

-0.14

Advisor

-0.14

 itself

-0.13

ÏģÎ¹Î±

-0.13

ukkit

-0.13

POSITIVE LOGITS

issen

0.19

odore

0.19

ses

0.18

kla

0.17

tas

0.17

oretical

0.17

ories

0.16

bes

0.16

/her

0.16

-mÃªme

0.15

Activations Density 0.049%

references to self in method calls or object properties

No Comments

No Known Activations