INDEX

Explanations

instances of direct speech or quotations within the text

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

Detach

-0.15

kou

-0.15

oko

-0.14

ãĥ¯ãĥ¼

-0.13

 cuckold

-0.13

Jeh

-0.13

.annot

-0.13

 Wheeler

-0.13

unks

-0.13

 Jacques

-0.13

POSITIVE LOGITS

 ÙĪØ£ÙĨ

0.18

æŁ

0.15

Edu

0.14

/Instruction

0.14

igy

0.14

 Hizmet

0.14

alam

0.14

Activations Density 0.254%

instances of direct speech or quotations within the text

No Comments

No Known Activations