INDEX

Explanations

references to colors and their associated meanings or contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

-0.15

legen

-0.15

ira

-0.15

quiring

-0.15

uong

-0.15

kup

-0.15

-0.14

kd

-0.14

POSITIVE LOGITS

-su

0.19

 haired

0.16

suit

0.16

kili

0.16

empt

0.16

istrict

0.15

-shirt

0.15

?url

0.15

-haired

0.15

bsite

0.15

Activations Density 0.059%

references to colors and their associated meanings or contexts

No Comments

No Known Activations