INDEX

Explanations

terms related to illegal activities and violations

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

adh

-0.17

inel

-0.16

/workspace

-0.15

rup

-0.15

onor

-0.15

BYTES

-0.15

ãģıãĤĭ

-0.15

rey

-0.15

levision

-0.15

out

-0.15

POSITIVE LOGITS

ities

0.31

/il

0.25

 aliens

0.22

StateException

0.21

 immigrants

0.20

ITIES

0.19

iti

0.19

 alien

0.19

 bahis

0.18

-imm

0.18

Activations Density 0.019%

terms related to illegal activities and violations

No Comments

No Known Activations