INDEX

Explanations

references to different historical or temporal eras

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

affen

-0.17

adem

-0.15

.ImageAlign

-0.15

erview

-0.15

ect

-0.15

atem

-0.14

ngine

-0.14

agger

-0.14

ieren

-0.14

enge

-0.14

POSITIVE LOGITS

-era

0.17

-long

0.17

-old

0.16

uden

0.16

era

0.15

ago

0.15

dition

0.15

icals

0.15

Ð¾ÑĢÑĤ

0.14

imitive

0.14

Activations Density 0.048%

references to different historical or temporal eras

No Comments

No Known Activations