INDEX

Explanations

references to programming or development terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

pent

-0.18

 Pros

-0.17

ags

-0.17

Pros

-0.16

aton

-0.16

Pro

-0.15

atsu

-0.15

esian

-0.15

 repro

-0.15

POSITIVE LOGITS

vision

0.23

pery

0.19

spect

0.19

portion

0.18

tein

0.18

ìłĿíĬ¸

0.17

 spect

0.17

visions

0.16

cura

0.16

ekt

0.16

Activations Density 0.031%

references to programming or development terminology

No Comments

No Known Activations