INDEX

Explanations

references to leadership roles and organizational involvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

Bea

-0.16

iras

-0.16

cht

-0.15

 Heller

-0.14

ala

-0.14

 Stam

-0.14

stk

-0.14

à¤¾à¤§à¤¨

-0.14

Bush

-0.14

unya

-0.14

POSITIVE LOGITS

ÅĽ

0.15

 scaleY

0.14

angan

0.14

jing

0.14

sburg

0.14

ppy

0.14

legation

0.14

FAILURE

0.13

leg

0.13

Activations Density 0.106%

references to leadership roles and organizational involvement

No Comments

No Known Activations