INDEX

Explanations

terms related to growth or increase

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ossal

-0.18

ESSAGES

-0.17

ession

-0.16

ulos

-0.15

ergus

-0.15

lint

-0.14

ize

-0.14

ization

-0.14

eter

-0.14

roc

-0.14

POSITIVE LOGITS

JKLMNOP

0.15

gate

0.15

infeld

0.14

ofday

0.14

uhl

0.13

kyt

0.13

ìĽĥ

0.13

vanished

0.13

/Foundation

0.13

Activations Density 0.029%

terms related to growth or increase

No Comments

No Known Activations