INDEX

Explanations

references to significant themes, events, or influential elements across various contexts

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

 Ð¾Ð±Ð¾

-0.15

 everywhere

-0.14

iet

-0.14

Ã¼Ã§

-0.14

 Graz

-0.13

ont

-0.13

 entire

-0.13

 entirety

-0.13

ÏĥÎ¼

-0.13

orem

-0.13

POSITIVE LOGITS

hte

0.16

åħ·

0.15

[assembly

0.15

obre

0.14

ones

0.14

 early

0.14

ht

0.14

hta

0.14

itution

0.14

Activations Density 0.146%

references to significant themes, events, or influential elements across various contexts

No Comments

No Known Activations