INDEX

Explanations

occurrences of the word "put" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ewire

-0.17

itez

-0.16

haust

-0.16

eden

-0.15

inventory

-0.15

stras

-0.15

Ð¾ÐºÐ°

-0.15

 Luft

-0.14

ening

-0.14

POSITIVE LOGITS

nam

0.21

atively

0.19

aker

0.18

 puts

0.18

ative

0.17

AKER

0.17

put

0.17

 emphasis

0.17

tin

0.16

put

0.16

Activations Density 0.064%

occurrences of the word "put" and its variations

No Comments

No Known Activations