INDEX

Explanations

the letter "T" in various contexts, indicating a focus on this specific character

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ouch

-0.24

ube

-0.23

asks

-0.21

akes

-0.21

ime

-0.20

ask

-0.20

ipo

-0.20

imer

-0.19

ools

-0.19

iny

-0.18

POSITIVE LOGITS

acon

0.23

dap

0.18

juana

0.18

etz

0.17

usz

0.16

nem

0.16

olan

0.16

ilton

0.15

eg

0.15

alm

0.15

Activations Density 0.032%

the letter "T" in various contexts, indicating a focus on this specific character

No Comments

No Known Activations