INDEX

Explanations

expressions of personal performance and self-assessment in competitive contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ementia

-0.17

.scalablytyped

-0.15

ora

-0.14

.LayoutParams

-0.14

 cáº§u

-0.14

åŃĿ

-0.14

.ops

-0.13

Hab

-0.13

 Melanie

-0.13

IBC

-0.13

POSITIVE LOGITS

Gay

0.15

ogn

0.15

-inst

0.14

iska

0.14

oji

0.14

stered

0.14

 rein

0.14

redi

0.14

ilar

0.13

odox

0.13

Activations Density 0.002%

expressions of personal performance and self-assessment in competitive contexts

No Comments

No Known Activations