INDEX

Explanations

references to authenticity or realness in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

iez

-0.15

ara

-0.15

ummies

-0.14

Og

-0.14

eno

-0.14

ummy

-0.14

ÐµÑĤÑĭ

-0.14

unday

-0.14

loh

-0.14

rama

-0.14

POSITIVE LOGITS

 actually

0.22

 actual

0.20

actually

0.19

 Actual

0.19

Actual

0.18

(actual

0.18

_actual

0.17

lia

0.17

actual

0.16

 real

0.16

Activations Density 0.329%

references to authenticity or realness in various contexts

No Comments

No Known Activations