INDEX

Explanations

year and date references

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

str

-0.17

inati

-0.15

 atom

-0.14

iggins

-0.14

ant

-0.13

 Newsletter

-0.13

Box

-0.13

Fot

-0.13

gut

-0.13

POSITIVE LOGITS

veis

0.17

icode

0.16

stu

0.15

mant

0.14

ÑĩÐ¸ÐºÐ¸

0.14

Arena

0.14

Mess

0.13

today

0.13

-navbar

0.13

MetaData

0.13

Activations Density 0.018%

year and date references

No Comments

No Known Activations