INDEX

Explanations

occurrences of the word "ford" in 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 @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

tres

-0.16

.idea

-0.15

.WinForms

-0.15

isa

-0.15

ÏĦÏģ

-0.14

Khu

-0.14

icorn

-0.14

contrast

-0.14

Du

-0.13

ira

-0.13

POSITIVE LOGITS

shire

0.17

oxel

0.15

okus

0.15

edics

0.14

ERVER

0.14

aging

0.14

akis

0.14

uche

0.14

yo

0.14

Activations Density 0.011%

occurrences of the word "ford" in various contexts

No Comments

No Known Activations