INDEX

Explanations

phrases that indicate the prevalence or commonality of certain opinions or behaviors among groups of people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

orc

-0.17

 sometimes

-0.16

itten

-0.15

Ã¥l

-0.15

assis

-0.14

orse

-0.14

eko

-0.14

 shouldn

-0.13

iber

-0.13

POSITIVE LOGITS

0.17

@param

0.17

Probably

0.15

 except

0.15

 Probably

0.15

iffies

0.15

arde

0.15

except

0.15

okud

0.14

heten

0.14

Activations Density 0.184%

phrases that indicate the prevalence or commonality of certain opinions or behaviors among groups of people

No Comments

No Known Activations