INDEX

Explanations

the presence of specific nouns and their relationships in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

Å©

-0.16

ARGIN

-0.15

áº½

-0.15

_variant

-0.15

Ĥ

-0.15

.protobuf

-0.15

prus

-0.15

idata

-0.14

arrera

-0.14

ÐºÐ¾Ð²Ð¾Ð¹

-0.14

POSITIVE LOGITS

0.14

igt

0.14

ag

0.14

 target

0.14

Context

0.14

iglia

0.14

 focus

0.13

 major

0.13

nam

0.13

key

0.13

Activations Density 0.102%

the presence of specific nouns and their relationships in context

No Comments

No Known Activations