INDEX

Explanations

references to reading and related activities

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

/by

-0.17

ades

-0.16

ats

-0.16

uso

-0.16

phem

-0.15

ated

-0.15

.bc

-0.15

 Butter

-0.15

am

-0.15

POSITIVE LOGITS

/watch

0.27

ied

0.20

/list

0.20

ults

0.20

/view

0.19

IED

0.17

iness

0.17

mitted

0.17

ertest

0.17

INESS

0.17

Activations Density 0.034%

references to reading and related activities

No Comments

No Known Activations