INDEX

Explanations

occurrences of the word "included"

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

ero

-0.16

umont

-0.14

acco

-0.13

ninger

-0.13

jom

-0.13

eres

-0.13

 Russo

-0.13

******/

-0.13

_aspect

-0.13

ertz

-0.13

POSITIVE LOGITS

obo

0.18

0.16

 Conte

0.15

oph

0.15

ipi

0.14

enant

0.14

ETIME

0.14

kle

0.14

aed

0.14

Activations Density 0.041%

occurrences of the word "included"

No Comments

No Known Activations