INDEX

Explanations

references to tug-of-war and associated actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

notated

-0.16

cheng

-0.15

oppel

-0.15

holm

-0.15

aus

-0.15

icina

-0.15

Ø¯

-0.14

icine

-0.14

akis

-0.14

ingular

-0.14

POSITIVE LOGITS

Ð¿ÑĢÐ°Ð²

0.16

.eq

0.15

eq

0.15

ishi

0.15

tel

0.14

evi

0.14

irc

0.14

onto

0.14

div

0.14

equ

0.13

Activations Density 0.006%

references to tug-of-war and associated actions

No Comments

No Known Activations