INDEX

Explanations

concepts related to biological and marketing structures or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

idden

-0.17

amat

-0.15

iate

-0.15

 pillar

-0.14

apat

-0.14

 ngang

-0.14

/doc

-0.14

pillar

-0.14

obo

-0.14

]|[

-0.13

POSITIVE LOGITS

\CMS

0.15

.scalablytyped

0.15

ãĥ§

0.14

Ð½Ð°ÑĢÑĥÐ¶

0.14

chsel

0.13

çł

0.13

ëŁ¼

0.13

kening

0.13

ysqli

0.13

ocode

0.13

Activations Density 0.085%

concepts related to biological and marketing structures or categories

No Comments

No Known Activations