INDEX

Explanations

references to specific characters or subjects in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

DIRECTORY

-0.16

ernote

-0.16

ough

-0.15

foon

-0.15

ÑĪÑĥ

-0.14

meer

-0.14

ylko

-0.14

elyn

-0.14

earch

-0.14

dney

-0.14

POSITIVE LOGITS

/us

0.19

igli

0.15

agues

0.15

htag

0.14

ander

0.14

edom

0.14

itzer

0.13

odies

0.13

sville

0.13

Activations Density 0.027%

references to specific characters or subjects in a narrative context

No Comments

No Known Activations