INDEX

Explanations

references to time-sensitive actions or outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ÅĻet

-0.18

uml

-0.17

igham

-0.17

illez

-0.15

ÑĢÐµÑģ

-0.14

ignite

-0.14

uche

-0.14

ntl

-0.14

ente

-0.14

 buflen

-0.14

POSITIVE LOGITS

 within

1.12

within

1.02

 Within

0.99

Within

0.93

_within

0.76

 dalam

0.60

 dentro

0.55

 dans

0.54

 binnen

0.54

à¸łà¸²à¸¢à¹ĥà¸Ļ

0.53

Activations Density 0.372%

references to time-sensitive actions or outcomes

No Comments

No Known Activations