INDEX

Explanations

terms related to business acquisitions and brand names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

arius

-0.17

ua

-0.16

oust

-0.15

ivalence

-0.15

conomy

-0.14

ury

-0.14

ivirus

-0.14

inary

-0.14

onio

-0.13

ham

-0.13

POSITIVE LOGITS

ycz

0.19

uese

0.17

loquent

0.15

 Loren

0.14

ewise

0.14

Å¾el

0.14

JNI

0.13

çļĦåľ°

0.13

ibName

0.13

ldr

0.13

Activations Density 0.260%

terms related to business acquisitions and brand names

No Comments

No Known Activations