INDEX

Explanations

relational and conditional phrases in dialogues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ystems

-0.15

 ÑģÑĥÑĤ

-0.15

Illuminate

-0.15

Ð±Ð°Ñĩ

-0.14

âĢŀD

-0.14

oltip

-0.14

iliar

-0.14

 Scout

-0.13

elik

-0.13

ãĥ«ãĤ¯

-0.13

POSITIVE LOGITS

ovÃ¡

0.17

aign

0.17

hle

0.16

 herself

0.16

phia

0.16

esh

0.15

dro

0.15

agle

0.15

nob

0.15

Dro

0.14

Activations Density 1.074%

relational and conditional phrases in dialogues

No Comments

No Known Activations