INDEX

Explanations

phrases that denote structure and organization in a formal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

aber

-0.16

esso

-0.15

ataire

-0.15

elman

-0.15

undred

-0.14

ãĥ¨

-0.14

ness

-0.13

,:,

-0.13

.compat

-0.13

anst

-0.13

POSITIVE LOGITS

 actual

0.23

 identical

0.23

usa

0.22

 majority

0.21

 particular

0.21

Usa

0.19

 sunday

0.19

 applying

0.19

actual

0.18

 potency

0.18

Activations Density 0.040%

phrases that denote structure and organization in a formal context

No Comments

No Known Activations