INDEX

Explanations

numerical data and dates within 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 @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

_tokenize

-0.14

ovenant

-0.14

mando

-0.14

ird

-0.14

ä¿®

-0.14

(\$

-0.14

ÑĢÐ°Ð±Ð°ÑĤ

-0.14

ìĦ

-0.13

POSITIVE LOGITS

 Flush

0.17

yers

0.15

aires

0.15

endon

0.15

aire

0.15

 flush

0.14

 ingredient

0.14

pac

0.14

ewise

0.14

Activations Density 0.026%

numerical data and dates within the text

No Comments

No Known Activations