INDEX

Explanations

pivotal events or actions that indicate significant outcomes or honors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 latest

-0.16

µ¬

-0.15

owell

-0.15

anno

-0.14

gn

-0.14

 lately

-0.14

mant

-0.14

 Latest

-0.14

atab

-0.13

Latest

-0.13

POSITIVE LOGITS

äºİ

0.19

 dated

0.19

date

0.16

 February

0.15

May

0.15

dated

0.15

 tanggal

0.15

 July

0.15

:date

0.15

_hyper

0.15

Activations Density 0.003%

pivotal events or actions that indicate significant outcomes or honors

No Comments

No Known Activations