INDEX

Explanations

references to specific segments or parts within a larger context or structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

CKET

-0.17

uled

-0.16

uler

-0.15

à¸«à¸§

-0.15

olib

-0.14

mam

-0.14

_hal

-0.14

Ð²Ð¾Ð»

-0.14

è¦

-0.14

reau

-0.13

POSITIVE LOGITS

azzi

0.15

aho

0.15

utters

0.14

ake

0.14

aw

0.14

aight

0.14

 maybe

0.14

adders

0.14

Nin

0.14

ushman

0.14

Activations Density 0.076%

references to specific segments or parts within a larger context or structure

No Comments

No Known Activations