INDEX

Explanations

proper nouns, particularly names associated with individuals and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

lus

-0.16

lom

-0.15

;element

-0.15

ither

-0.15

ifornia

-0.15

unable

-0.14

 straw

-0.14

hled

-0.14

edy

-0.14

chner

-0.13

POSITIVE LOGITS

aka

0.24

aka

0.19

AK

0.16

ptides

0.15

orb

0.15

andas

0.15

 nick

0.14

 çĨ

0.14

 yani

0.14

Activations Density 0.807%

proper nouns, particularly names associated with individuals and locations

No Comments

No Known Activations