INDEX

Explanations

questions related to technical problems in software or hardware implementations

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

çĸ

-0.15

/column

-0.13

_HINT

-0.13

 ìĹ¬ëŁ¬ë¶Ħ

-0.13

autop

-0.13

itere

-0.13

æķ·

-0.12

olio

-0.12

%f

-0.12

yla

-0.12

POSITIVE LOGITS

 somehow

0.16

.physics

0.15

something

0.14

getSingleton

0.14

 something

0.14

 unspecified

0.14

utin

0.14

0.13

ought

0.13

icked

0.13

Activations Density 0.129%

questions related to technical problems in software or hardware implementations

No Comments

No Known Activations