INDEX

Explanations

names, particularly those associated with crime or scandals

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

oog

-0.20

ovel

-0.19

ed

-0.18

iag

-0.18

iens

-0.16

ovsky

-0.16

ogie

-0.16

eses

-0.16

oton

-0.16

ogs

-0.15

POSITIVE LOGITS

rr

0.26

ington

0.22

inger

0.22

0.21

era

0.20

amient

0.20

icks

0.20

ick

0.19

ort

0.19

itt

0.19

Activations Density 0.022%

names, particularly those associated with crime or scandals

No Comments

No Known Activations