INDEX

Explanations

references to various governmental or organizational entities, particularly focused on agencies and agents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ances

-0.16

uously

-0.16

ÑģÑı

-0.15

scient

-0.15

ulan

-0.14

ELY

-0.14

mae

-0.14

achines

-0.14

unce

-0.14

ìį¨

-0.14

POSITIVE LOGITS

ing

0.27

 provoc

0.25

wide

0.20

errupted

0.17

ive

0.16

ors

0.16

 Lone

0.16

gy

0.16

ging

0.16

.uk

0.15

Activations Density 0.042%

references to various governmental or organizational entities, particularly focused on agencies and agents

No Comments

No Known Activations