INDEX

Explanations

key concepts related to philosophical and ethical discussions about power dynamics and conduct

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ENCHMARK

-0.14

(es

-0.14

ÄįÃŃ

-0.14

RL

-0.14

tier

-0.13

porter

-0.13

ãĥĬãĥ¼

-0.13

Ð»Ð¸Ñĩ

-0.13

.edu

-0.13

POSITIVE LOGITS

IIIK

0.14

 Wolff

0.14

eldom

0.14

ãĥ

0.13

GMEM

0.13

lov

0.13

 à¤īà¤ł

0.13

YPRE

0.13

åİļ

0.12

chedule

0.12

Activations Density 0.365%

key concepts related to philosophical and ethical discussions about power dynamics and conduct

No Comments

No Known Activations