INDEX

Explanations

references to locations and organizational structures

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

hci

-0.20

gles

-0.16

ERIC

-0.16

omanip

-0.15

Wiki

-0.15

ural

-0.14

ichier

-0.14

wsz

-0.14

vale

-0.14

.MixedReality

-0.14

POSITIVE LOGITS

bi

0.16

ar

0.15

ë°°

0.15

ft

0.14

ken

0.14

Master

0.14

env

0.14

acz

0.14

shima

0.14

Activations Density 0.501%

references to locations and organizational structures

No Comments

No Known Activations