INDEX

Explanations

negations and conditional statements

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

esar

-0.14

mac

-0.14

isable

-0.14

 underground

-0.14

oi

-0.14

Ve

-0.14

.o

-0.14

able

-0.14

Ve

-0.14

ighet

-0.13

POSITIVE LOGITS

ctors

0.16

emento

0.16

ahren

0.16

akov

0.16

 Spoon

0.15

SSIP

0.15

&type

0.15

auge

0.15

bis

0.15

SPARENT

0.15

Activations Density 0.001%

negations and conditional statements

No Comments

No Known Activations