INDEX

Explanations

occurrences of years in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ambi

-0.16

linger

-0.16

rror

-0.15

stock

-0.15

iros

-0.14

malink

-0.14

anÄ±

-0.13

 correct

-0.13

ningar

-0.13

elix

-0.13

POSITIVE LOGITS

rome

0.15

?action

0.15

ãĥªãĤ¹

0.15

idos

0.14

sov

0.14

ispers

0.14

CharArray

0.14

Gib

0.14

ILLISE

0.14

iswa

0.13

Activations Density 0.044%

occurrences of years in the text

No Comments

No Known Activations