INDEX

Explanations

the phrase "to see" and its variations, indicating anticipation or expectation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ly

-0.18

hev

-0.16

irk

-0.15

SEA

-0.15

yla

-0.14

 å·Ŀ

-0.14

rio

-0.14

erv

-0.14

Lar

-0.14

yl

-0.14

POSITIVE LOGITS

0.15

 Sass

0.14

Ú¯Ø§ÙĨÛĮ

0.14

ISTA

0.14

çīĪ

0.14

.soft

0.14

igans

0.14

agens

0.14

eneg

0.14

enia

0.14

Activations Density 0.017%

the phrase "to see" and its variations, indicating anticipation or expectation

No Comments

No Known Activations