INDEX

Explanations

references to influential figures and their actions within a socio-political context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ÅĽÄĩ

-0.17

-Men

-0.16

ROID

-0.16

 Ø¯Ø§Ø®

-0.15

ãĥ¼ãĥ³

-0.15

Å¡li

-0.15

 serr

-0.15

 Lanka

-0.15

suppress

-0.14

.localized

-0.14

POSITIVE LOGITS

inder

0.33

 Singh

0.29

Sing

0.27

INDER

0.27

 sing

0.27

 Gill

0.26

jit

0.25

bir

0.24

pre

0.23

 Parm

0.23

Activations Density 0.057%

references to influential figures and their actions within a socio-political context

No Comments

No Known Activations