INDEX

Explanations

references to specific locations or conditions within a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.16

ymb

-0.16

 ãĤ¸ãĥ£

-0.16

unce

-0.15

ADX

-0.14

hoff

-0.14

æĥħ

-0.13

 Hindered

-0.13

 AssertionError

-0.13

xBD

-0.13

POSITIVE LOGITS

hon

0.17

ellan

0.15

iggins

0.15

Dum

0.15

 fasc

0.14

°

0.14

elho

0.14

veis

0.14

must

0.14

thumbnail

0.14

Activations Density 0.175%

references to specific locations or conditions within a context

No Comments

No Known Activations