INDEX

Explanations

occurrences of the word "last" with different contexts

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

erge

-0.16

istrator

-0.15

POSITE

-0.14

arts

-0.14

.ov

-0.14

rch

-0.14

ouses

-0.14

ano

-0.13

pace

-0.13

etting

-0.13

POSITIVE LOGITS

maal

0.15

-await

0.14

alaxy

0.14

brook

0.14

anza

0.14

UNCH

0.14

abra

0.13

ouncing

0.13

illes

0.13

cps

0.13

Activations Density 0.028%

occurrences of the word "last" with different contexts

No Comments

No Known Activations