INDEX

Explanations

references to changes, amendments, and modifications in procedural contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

iaux

-0.16

ÑĤ

-0.16

illow

-0.15

 loads

-0.15

IFI

-0.15

nam

-0.15

 Bord

-0.14

ÑĤÐ¾Ð²

-0.14

Bog

-0.14

illes

-0.14

POSITIVE LOGITS

lew

0.15

/Add

0.15

pace

0.15

orch

0.15

_mime

0.15

enga

0.15

ux

0.14

Î±Î½Î´

0.14

ãĥĹãĥ¬

0.14

ovsky

0.14

Activations Density 0.268%

references to changes, amendments, and modifications in procedural contexts

No Comments

No Known Activations