INDEX

Explanations

occurrences of the word "found" 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

Ð°Ñħ

-0.14

toi

-0.14

offee

-0.14

.sb

-0.14

Ã³d

-0.13

wal

-0.13

MB

-0.13

dad

-0.13

ÐĴÐ¡

-0.13

ilia

-0.13

POSITIVE LOGITS

yang

0.17

pond

0.16

ê¼

0.14

roid

0.14

CHANT

0.14

ries

0.14

pro

0.14

Pocket

0.14

bury

0.14

hop

0.13

Activations Density 0.028%

occurrences of the word "found" in various contexts

No Comments

No Known Activations