INDEX

Explanations

programming-related syntax and structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 Dillon

-0.15

ija

-0.15

linkplain

-0.14

abei

-0.14

 assignable

-0.14

loyd

-0.14

anten

-0.13

ines

-0.13

 thuáºŃt

-0.13

imde

-0.13

POSITIVE LOGITS

iffer

0.18

WithString

0.16

OMET

0.16

ÏįÏĦÎµ

0.15

pais

0.15

 Clarkson

0.14

znik

0.14

uÅŁ

0.14

ãĥ¾

0.14

Activations Density 0.028%

programming-related syntax and structure

No Comments

No Known Activations