INDEX

Explanations

references to programming or technical documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ugins

-0.15

 Side

-0.15

rippling

-0.14

plaintext

-0.14

pNet

-0.14

 Patri

-0.14

attern

-0.14

eway

-0.13

igi

-0.13

 consectetur

-0.13

POSITIVE LOGITS

 Sands

0.18

ats

0.15

slo

0.15

esin

0.14

cox

0.14

pus

0.13

Launch

0.13

hur

0.13

gota

0.13

_pd

0.13

Activations Density 0.000%

references to programming or technical documentation

No Comments

No Known Activations