INDEX

Explanations

terms related to nature and biological classification

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

Î¹ÏĥÏĦÎ¿

-0.16

 Cons

-0.14

AUX

-0.14

pole

-0.14

uffle

-0.14

enson

-0.14

 Kens

-0.13

angler

-0.13

usto

-0.13

nearest

-0.13

POSITIVE LOGITS

Łèĥ½

0.16

 duplic

0.16

ssp

0.15

iyet

0.15

.Range

0.15

 Kramer

0.15

Du

0.15

 Pant

0.14

kyt

0.14

Activations Density 0.065%

terms related to nature and biological classification

No Comments

No Known Activations