INDEX

Explanations

references to relevant information or topics within a text

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

olley

-0.20

ÄĽÅ¾

-0.16

utut

-0.14

keys

-0.14

flake

-0.14

atto

-0.14

ernet

-0.14

.languages

-0.14

ÑĨÐ¾Ð²

-0.14

sheet

-0.14

POSITIVE LOGITS

UME

0.15

oti

0.14

INTR

0.14

Ð°Ð½Ðµ

0.14

.nb

0.13

ìĭĿ

0.13

conv

0.13

 comp

0.13

Ã°

0.13

kan

0.13

Activations Density 0.027%

references to relevant information or topics within a text

No Comments

No Known Activations