INDEX

Explanations

phrases related to programming, particularly assertions and error handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

zl

-0.17

UIApplication

-0.14

nelle

-0.14

aData

-0.14

dy

-0.14

DY

-0.14

ROTO

-0.14

UCT

-0.14

.trip

-0.14

elsea

-0.13

POSITIVE LOGITS

atham

0.15

atro

0.15

ucher

0.15

ãĥ¥

0.14

.pref

0.14

atha

0.14

0.13

ish

0.13

prises

0.13

Activations Density 0.012%

phrases related to programming, particularly assertions and error handling

No Comments

No Known Activations