INDEX

Explanations

key verbs and related concepts that indicate actions or explanations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ALA

-0.17

bourg

-0.16

 shade

-0.16

oppins

-0.15

kos

-0.15

 mess

-0.14

urers

-0.14

upport

-0.14

æĶ¯

-0.14

POSITIVE LOGITS

SSIP

0.16

onz

0.16

Î¼ÏĨ

0.15

/Game

0.15

hin

0.15

 Goodman

0.14

olem

0.14

isy

0.14

.UnitTesting

0.13

(crate

0.13

Activations Density 0.005%

key verbs and related concepts that indicate actions or explanations

No Comments

No Known Activations