INDEX

Explanations

phrases indicating actions or intentions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

inen

-0.17

Ð¼Ð¾Ð¼

-0.15

orf

-0.15

ella

-0.14

iani

-0.14

Ð¾Ð»Ð¾Ð¼

-0.14

hana

-0.13

uen

-0.13

ocoder

-0.13

PointF

-0.13

POSITIVE LOGITS

ITU

0.16

tual

0.16

cret

0.15

aeda

0.15

tors

0.15

0.14

ilters

0.14

abbo

0.14

aign

0.14

Activations Density 0.024%

phrases indicating actions or intentions

No Comments

No Known Activations