INDEX

Explanations

references to Hinduism and associated concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

izard

-0.16

chw

-0.16

nels

-0.15

 háº¡ng

-0.15

 distortion

-0.15

 organ

-0.15

nel

-0.14

nelle

-0.14

jedn

-0.14

Coroutine

-0.14

POSITIVE LOGITS

ÄĻp

0.15

oure

0.14

Ð¾Ð½Ñĭ

0.14

onz

0.14

ostat

0.13

/locale

0.13

 specifics

0.13

oreach

0.13

Activations Density 0.012%

references to Hinduism and associated concepts

No Comments

No Known Activations