INDEX

Explanations

references to data privacy and genetic information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

lej

-0.15

ichni

-0.14

vala

-0.14

_ue

-0.13

Ã¡ct

-0.13

ilha

-0.13

 tiener

-0.13

endregion

-0.12

regar

-0.12

ruba

-0.12

POSITIVE LOGITS

 counterpart

0.65

 equivalents

0.62

 equivalent

0.60

 counterparts

0.58

 Equivalent

0.51

 analogue

0.49

 analog

0.46

 alternatives

0.46

 alternative

0.45

 Ð°Ð½Ð°Ð»Ð¾Ð³

0.45

Activations Density 0.310%

references to data privacy and genetic information

No Comments

No Known Activations