INDEX

Explanations

programming-related syntax and structures

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

ussen

-0.18

rim

-0.16

RunWith

-0.14

 VÅ¡ech

-0.14

kov

-0.14

agan

-0.13

DBNull

-0.13

 Invisible

-0.13

myp

-0.13

riv

-0.13

POSITIVE LOGITS

int

0.25

 boolean

0.20

 bool

0.18

boolean

0.16

int

0.16

 float

0.16

 string

0.15

int

0.15

 McCabe

0.15

strings

0.14

Activations Density 0.026%

programming-related syntax and structures

No Comments

No Known Activations