INDEX

Explanations

assert statements in testing code

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

kes

-0.18

atan

-0.17

ths

-0.16

lets

-0.16

ught

-0.15

.IsNull

-0.15

[__

-0.15

ansi

-0.15

vsp

-0.14

afil

-0.14

POSITIVE LOGITS

quential

0.17

avia

0.14

igy

0.14

conde

0.14

uben

0.14

ifies

0.14

edio

0.13

fas

0.13

Activations Density 0.005%

assert statements in testing code

No Comments

No Known Activations