INDEX

Explanations

mentions of presentations

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

-0.16

pin

-0.16

 Bans

-0.15

olas

-0.15

ogram

-0.15

ogn

-0.15

OTT

-0.14

azes

-0.14

na

-0.14

alis

-0.14

POSITIVE LOGITS

phis

0.16

UNE

0.16

ENCIL

0.15

ilib

0.15

WithDuration

0.15

 NÄĽm

0.14

 voks

0.14

ãĥ£

0.14

[...,

0.14

ellig

0.14

Activations Density 0.012%

mentions of presentations

No Comments

No Known Activations