INDEX

Explanations

the pronoun "this."

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

ä¸Ī

-0.17

ieri

-0.16

sec

-0.15

enth

-0.14

ific

-0.14

HIGH

-0.14

stad

-0.13

infer

-0.13

uche

-0.13

POSITIVE LOGITS

chl

0.16

aley

0.15

aceous

0.14

³

0.14

ãĤ¿ãĥ¼

0.13

elters

0.13

idelberg

0.13

 Ø·ÙĪØ±

0.13

icopter

0.13

ë¬

0.13

Activations Density 0.004%

the pronoun "this."

No Comments

No Known Activations